Mobile game-based learning presents a potential avenue for vocabulary acquisition in English language learning, yet research on students’ perceptions of specific platforms is limited. This study focuses on investigating Grade 9 students’ perceptions of using Alef Education, an AI-based digital platform, for English vocabulary learning in North Sumatra, Indonesia. The purpose is to explore how gamification and multimodal approaches affect learning motivation and vocabulary retention. Using a descriptive qualitative method with a phenomenological perspective, data were collected through participatory observation and semi-structured interviews with ten students aged 14–15. Findings reveal that gamified features significantly enhance motivation, and the multimodal approach combining text, audio, and visuals improves vocabulary retention and application. However, technical issues and limited teacher interaction hinder effectiveness. This study highlights the importance of addressing both motivational and practical barriers in digital platforms. These insights inform strategies to optimize game-based learning for vocabulary acquisition in EFL contexts.