Sentipolis: Emotion-Aware Agents for Social Simulations

TL;DR

Sentipolis introduces an emotion-aware framework for social simulation agents that maintains emotional continuity and improves grounded behavior using continuous PAD representation and emotion-memory coupling.

Contribution

It presents a novel emotionally stateful agent framework integrating continuous emotion modeling, dual-speed dynamics, and memory coupling for social simulations.

Findings

Enhanced emotional continuity in agent interactions.

Model-dependent improvements in believability.

Moderate impact on adherence to social norms.

Abstract

LLM agents are increasingly used for social simulation, yet emotion is often treated as a transient cue, causing emotional amnesia and weak long-horizon continuity. We present Sentipolis, a framework for emotionally stateful agents that integrates continuous Pleasure-Arousal-Dominance (PAD) representation, dual-speed emotion dynamics, and emotion--memory coupling. Across thousands of interactions over multiple base models and evaluators, Sentipolis improves emotionally grounded behavior, boosting communication, and emotional continuity. Gains are model-dependent: believability increases for higher-capacity models but can drop for smaller ones, and emotion-awareness can mildly reduce adherence to social norms, reflecting a human-like tension between emotion-driven behavior and rule compliance in social simulation. Network-level diagnostics show reciprocal, moderately clustered, and temporally stable relationship structures, supporting the study of cumulative social dynamics such as alliance formation and gradual relationship change.