Towards robot affective appraisal linking inner speech and emotion

Recent studies in Robotics and AI suggest that robots “thinking out loud” can foster positive human feedback and support collaborative goal achievement. By externalizing their internal reasoning, robots enhance transparency and explainability, which are crucial for trust and robustness in human–robot interaction. This work investigates the role of robot inner speech in supporting affective appraisal, focusing on the emergence, coherence, and interpretability of emotionally grounded evaluations. While the relationship between inner speech and emotion has been extensively explored within human psychology and cognitive science, this work is the first to operationalize this connection within a robotic architecture for affective appraisal. Grounded in appraisal theories, the proposed model employs inner speech to simulate internal reflection, enabling the identification and evaluation of contextual variables relevant to affective assessment. Through this internal dialogue, the robot structures its appraisal process and externalizes it, allowing human partners to access and interpret the underlying affective reasoning. The model is evaluated by comparing its appraisal dynamics with normative emotional patterns observed in adults under stress, and by assessing the interpretability of the robot’s affective behavior through human observation. Results indicate that the model produces coherent and context-sensitive evaluations, improving upon a widely adopted computational model of emotion in terms of plausibility and transparency.