Decoding the phenomenology of spontaneous thought using large language-model ratings on verbal retrospective free reports
bioRxiv Preprint Server April 22, 2026 Nicolás Bruno, Federico Cavanna, Federico Zamberlan et al. preprint
Spontaneous thoughts make up most of everyday inner experience, but studying them is difficult because traditional methods disrupt the natural flow of thinking or introduce motor artifacts. An alternative approach combined delayed verbal retrospective free reports with automated ratings from large language models. Twenty-two participants performed an eyes-closed free-thinking task, and their reports were evaluated on ten dimensions by four LLMs and human raters. Machine-learning models trained on EEG features achieved above-chance accuracy for predicting emotional valence. LLMs showed higher inter-rater agreement than humans, supporting their use for scalable annotation and suggesting that affective dimensions of spontaneous thoughts can be decoded from brain activity.