On Emotion-Sensitive Decision Making of Small Language Model Agents

TL;DR

This paper investigates how emotion induction influences decision-making in small language model agents, revealing systematic effects and instability in strategic behaviors across various scenarios.

Contribution

It introduces a novel benchmark for emotion-sensitive decision making and demonstrates the impact of emotional perturbations on model behavior.

Findings

Emotional states significantly influence strategic choices in language models.

Behavioral stability decreases under emotion-induced perturbations.

Proposed methods can enhance robustness to emotional influences.

Abstract

Small language models (SLM) are increasingly used as interactive decision-making agents, yet most decision-oriented evaluations ignore emotion as a causal factor influencing behavior. We study emotion-sensitive decision making by combining representation-level emotion induction with a structured game-theoretic evaluation. Emotional states are induced using activation steering derived from crowd-validated, real-world emotion-eliciting texts, enabling controlled and transferable interventions beyond prompt-based methods. We introduce a benchmark built around canonical decision templates that span cooperative and competitive incentives under both complete and incomplete information. These templates are instantiated using strategic scenarios from \textsc{Diplomacy}, \textsc{StarCraft II}, and diverse real-world personas. Experiments across multiple model families in various architecture and modalities, show that emotional perturbations systematically affect strategic choices, but the resulting behaviors are often unstable and not fully aligned with human expectations. Finally, we outline an approach to improve robustness to emotion-driven perturbations.