On Emotion-Sensitive Decision Making of Small Language Model Agents

Small language models 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 Diplomacy, 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. The study is categorized under Artificial Intelligence, and can be cited as arXiv:2604.06562 [cs.AI] or arXiv:2604.06562v1 [cs.AI] for this version, with a DOI of https://doi.org/10.48550/arXiv.2604.06562, which was issued by arXiv via DataCite, pending registration. The submission history indicates that the study was submitted by Jiaju Lin, with the first version being submitted on Wednesday, 8 Apr 2026 01:24:13 UTC, with a file size of 1,798 KB.