Learning a Foreign Language is crucial in today’s interconnected world, as it enhances cross-cultural communication and fosters personal growth. Despite its many benefits, learners often face significant challenges, primarily due to Anxiety. To address these challenges, we introduce ELLA, a Dutch tutoring system powered by GPT-4. ELLA features an innovative Episodic Memory architecture, enabling learners to review and delete system-generated episodes from past interactions, thereby giving them a sense of control. Through this thesis, we explore the impact of Episodic Memory on Foreign Language Learners' Speaking Anxiety and the associated learning benefits. The investigation is divided into four sub-questions: the relationship between Foreign Language Anxiety and Language Learning, the optimization of the Episodic Memory framework for Learning, the influence of Episodic Memory on speaking-related State Anxiety, and the perceived benefits for learners with Foreign Language Anxiety. Our experimental study demonstrated that ELLA has the potential to reduce speaking-related State Anxiety in Dutch learners and offers significant learning benefits as perceived by users. However, areas for improvement are identified, such as the need for an Automatic Speech Recognition system that accurately recognizes foreign accents and a Large Language Model fine-tuned for the Language Learning task. Future research should focus on these enhancements, evaluate the system in different languages using standardized pre-and post-tests, and involve longer interactions with a larger and more diverse user base over time.