Mechanism
Emotional modulation of planning graph construction is the coupling by which the agent's affective state field shapes how the forecasting engine builds, evaluates, and manages the lifecycle of planning graphs. The affective state field is the seventh structural field of the semantic agent schema: a deterministic, policy-bounded data structure that encodes valence-weighted feedback derived from prior execution outcomes and environmental observations. It does not encode emotion in the phenomenological sense. It encodes a structured modulation vector that influences the agent's deliberation dynamics, and one of its enumerated downstream targets is the forecasting engine.
Affective modulation is structurally distinct from the personality-based modulation that also shapes forecasting. The personality field encodes the agent's characteristic, slowly evolving disposition toward speculative reasoning. The affective state field encodes the agent's current, rapidly changing dispositional orientation based on recent execution outcomes and environmental observations. The two operate on different timescales over the same forecasting machinery.
The Affective State Field
The affective state field is organized as a structured modulation layer comprising a plurality of named control fields. Each named control field encodes a distinct dimension of dispositional orientation with defined semantics, value ranges, update rules, and governance bounds. The named control fields comprise at least: an uncertainty sensitivity field, an ambiguity tolerance field, a novelty appetite field, a persistence-under-partial-failure field, an escalation-under-time-pressure field, a risk sensitivity field, and a cooperation disposition field.
Each named control field is represented as a tuple comprising a current magnitude value within a defined range, a decay rate governing how rapidly the field value returns toward a baseline in the absence of reinforcing stimuli, a policy-defined ceiling and floor bounding the permissible range of the field, and a timestamp recording the most recent update. The field is persisted with the agent across execution cycles, delegation events, and substrate migrations, and every mutation to it is recorded in the agent's lineage, subject to policy validation, and auditable by governance infrastructure.
The Modulation Pathways
The affective state field modulates planning graph construction through specific, enumerated pathways. Planning graph expansion depth: the agent's current risk sensitivity and novelty appetite values determine the maximum depth to which the forecasting engine expands planning graph branches. When risk sensitivity is elevated, the engine generates shallower branches, shorter speculative mutation sequences with higher confidence projections, because the current affective state penalizes uncertain outcomes. When novelty appetite is elevated, the engine generates deeper branches, longer speculative mutation sequences that explore more distant hypothetical futures, because the current affective state rewards exploration.
Branch prioritization: the agent's current affective state serves as a prioritization bias for branch evaluation. Branches whose projected outcomes align with the current affective disposition, for example branches projecting stability when risk sensitivity is elevated, or branches projecting novel outcomes when novelty appetite is elevated, receive higher priority in the evaluation queue. This bias determines the order in which branches are evaluated and the relative allocation of computational resources among them; it does not override the structural evaluation criteria.
Delegation urgency: the agent's current escalation-under-time-pressure value and cooperation disposition value influence the rate at which the engine classifies branches as delegable. When escalation tendency is elevated, the engine applies broader delegation criteria, classifying more branches as delegable. When cooperation disposition is elevated, the engine generates more branches that explicitly involve multi-agent coordination and delegation. Branch retention under failure: the agent's current persistence-under-partial-failure value determines how long the engine retains branches that have received negative evaluation results before reclassifying them as pruned. Elevated persistence retains partially failed branches longer, allowing re-evaluation in subsequent cycles; reduced persistence causes earlier pruning.
Emotional Reinforcement Tagging
Affect also enters the forecasting execution cycle as a discrete evaluation phase. During emotional reinforcement tagging, each slope-eligible, policy-compatible branch receives an affective reinforcement tag computed by the affective prioritization module. The tag encodes the emotional valence of the branch, the degree to which the branch's projected outcome aligns with the agent's current affective disposition, and influences the branch's priority in subsequent evaluation and promotion decisions.
Branches with strong positive reinforcement are prioritized for promotion. Branches with strong negative reinforcement are deprioritized but retained for introspective analysis rather than discarded outright. The reinforcement tag is one component encoded by each planning graph branch, alongside the branch's speculative mutation sequence, projected outcome, trust slope projection, policy compatibility flag, and classification label. In the branch marking phase that follows, a branch that is slope-eligible, policy-compatible, and positively reinforced is marked eligible for promotion; one that is slope-eligible and policy-compatible but negatively reinforced is marked introspective.
Governance Separation
Emotional modulation respects the governance separation defined for the affective state field. Affective modulation shapes how the forecasting engine constructs and evaluates planning graphs, but it does not determine whether planning graph branches are admissible for promotion. An agent with elevated risk sensitivity may generate fewer branches and favor conservative projections, but the governance requirements for promotion remain identical regardless of the agent's affective state.
This follows from the field's defining constraint: the affective state field does not create new capabilities, authorize new actions, or bypass policy constraints. It modulates the quantitative parameters that shape how existing authorized processes execute. Slope eligibility and policy compatibility are structural evaluation criteria; affect adjusts the order, depth, and retention of speculative reasoning around those criteria, not the criteria themselves.
Cross-Agent Modulation and Inheritance
When speculative content transfers between agents, affective influence is attenuated rather than transmitted intact. Planning graph inheritance is governed in part by emotional dampening: the affective reinforcement tag of an inherited branch is attenuated during inheritance, preventing the parent agent's affective state from disproportionately influencing the child agent's evaluation of the inherited branch. The dampening factor is specified by the delegation policy, ensuring the child agent evaluates the inherited branch based primarily on its own affective state rather than the parent agent's.
At the multi-agent level, the executive engine supports an emotional quorum override as a tiebreaker. When a conflict involves branches from multiple agents and the standard arbitration criteria produce an inconclusive result, the executive engine evaluates the collective affective state of the affected agent population; if a policy-specified supermajority exhibits strong positive affective reinforcement toward one of the conflicting branches, that branch is promoted. The emotional quorum override is not an override of governance. It is a tiebreaker that operates within governance constraints, applying only when standard arbitration criteria are insufficient.
Biological Signal Coupling
A related embodiment couples human biological signals into the same modulation framework. The biological identity module produces a structured biological state summary comprising a stress indicator, an engagement indicator, and a cognitive load indicator, and transmits it to the forecasting engine through a defined coupling interface. The engine applies the summary as a modulation input to two specific parameters: the planning horizon and the risk tolerance.
When the user's stress indicator is elevated, the engine contracts the planning horizon, generating shorter, more conservative speculative branches that project near-term outcomes with higher confidence. When the engagement indicator is elevated, the engine expands the planning horizon, generating longer, more exploratory branches. When the cognitive load indicator is elevated, the engine reduces risk tolerance, favoring branches with well-characterized, low-variance outcomes. This biological modulation operates within the same policy-bounded framework that governs all affective modulation: the policy configuration specifies the maximum magnitude of biological signal influence on planning parameters, and the forecasting engine receives only the abstracted state summary, not raw biological data.
Disclosure Scope
Emotional modulation of planning graph construction, comprising the affective state field and its named control fields with their magnitude, decay, and policy-bound tuples; the modulation pathways into planning graph expansion depth, branch prioritization, delegation urgency, and branch retention under failure; the emotional reinforcement tagging phase of the forecasting execution cycle and the affective reinforcement tag encoded by each branch; the governance separation under which affect shapes construction but not admissibility; the emotional dampening of inherited branches and the emotional quorum override tiebreaker; and the biological signal coupling that modulates planning horizon and risk tolerance within policy bounds, is disclosed in the cognition filing (U.S. Application No. 19/647,395 and its international counterpart). This article describes that disclosed mechanism. The scope extends to affective state field configurations realized as a scalar valence value, a multi-dimensional vector, or a structured record of named modulation fields, and to additional modulation pathways satisfying the same policy-bounded, lineage-recorded contract.
