The purpose of this study is to examine the effects of generative AI on technostress among second language (L2) English students at two Japanese universities. While the use of generative AI technologies in education is rapidly increasing, research on how these tools impact learners’ psychological well-being—particularly in L2 learning contexts—remains limited. This study primarily aimed to explore students’ experiences of generative AI–related technostress. In addition, a secondary analysis examining whether technostress levels varied by students’ language proficiency was conducted, although no significant differences were observed. A total of 100 L2 English students, 60 beginner learners and 40 intermediate-advanced learners, fully completed the survey, which consisted of Likert-scale and open-ended written response items. While the quantitative results indicated that the participants did not exhibit high levels of technostress, the qualitative findings suggested a more nuanced picture of the impact of AI-related technostress on university L2 students. Namely, the students were concerned about the accuracy of AI output and thus desired explicit training and guidance. These results indicate that while generative AI may not cause significant levels of technostress, the emerging technology still presents specific challenges that must be addressed. The article concludes with practical suggestions for language teachers and institutions so that they can better support L2 students’ AI literacy and reduce the risks of technostress.

Focusing on the global trend of artificial intelligence (AI) in language learning, this survey-based study explored the practices and perceptions of Japanese English as a foreign language students (EFL) toward ChatGPT for second language (L2) learning. A mixed-method research design was utilized to achieve the study’s aims, with data being collected from three universities in Japan. The technology acceptance model-based survey was administered in the fall of 2023 and a total of 521 EFL students fully completed it. Quantitative analysis related to the students’ practices revealed that less than 25% of the respondents had used ChatGPT in their English studies, with formal language learning being more common than informal L2 learning outside of English coursework. Summarizing information written in the English language and translation were the top reported uses of ChatGPT for L2 English learning. According to the Likert scale responses, the L2 students’ perceived usefulness, perceived ease of use, and behavioral intention to use ChatGPT for English learning were positive. Content analysis of the qualitative data indicated contrasting findings, namely, while the students believed the AI chatbot could enhance their L2 learning, they were also concerned that it could hinder their language learning if overly relied upon. These results indicate that although a growing number of L2 learners are using ChatGPT and perceive it to be a useful resource for language learning, they are also aware of the drawbacks it poses to the language learning process.