This presentation is based on a collaborative research project with Tadashi Iwami (Hokkaido University) and Marc Barcelos (Aarhus University), exploring how Japan’s longest-serving prime minister Abe Shinzō strategically used emotional rhetoric to garner international support for his Free and Open Indo-Pacific (FOIP) vision. The study introduces an innovative methodology using Bidirectional Encoder Representations from Transformers (BERT), a machine learning model capable of detecting and analysing syntax-sensitive emotional expressions in texts. Alongside presenting key findings, the talk offers a critical reflection on the opportunities and limitations of AI-based approaches to discourse analysis of Japanese texts, highlighting the important role Japan Studies can play in shaping scholarly engagement with digital transformation and computational methods in the humanities and social sciences.