摘要：Training the capacity to self-generate emotions can be a potent "vaccine" against negative stressors and be an effective intervention for affective psychopathology. However, due to a lack of knowledge about sources of individual differences in generation abilities, it is unclear how to optimally design such interventions. We investigated one potential source of variation, namely preference for using different information modalities (Visual Imagery, Auditory Imagery, Bodily Interoception, and Semantic Analysis). A representative sample of 293 participants self-induced positive and negative emotional states, freely choosing to use these modalities singly or in combination. No evidence was found for modality usage being associated with differential efficacy at generating of positive or negative emotion. Rather, usage of all modalities (except Auditory Imagery) predicted success at generation of both positive and negative emotional states. Increasing age predicted capacity to generate, especially negative, emotions. While no specific combinations of modalities were superior, the overall degree to which participants adopted multimodal implementations did predict generation efficacy. These findings inform interventions aimed at improving emotional self-generation, suggesting these must be mindful of individual differences in generation abilities and implementation tendencies, and that they should focus on enhancing the capacity to use multiple modalities.
