Emotion detection in textual data plays an important role in various NLP applications and is an important branch of sentiment analysis. There is a dearth of applications of emotion detection in low resource languages such as Hindi. There are a number of challenges in the available open-source resources in Hindi language such as imbalanced datasets and lack of understanding of textual nuances specific to Hindi. This paper presents a comprehensive study on emotion detection in Hindi text using Large Language Models (LLMs). We will be leveraging GPT-3.5-turbo API for dataset augmentation using few-shot learning and zero-shot learning techniques and further fine-tuning pretrained BERT and mBERT models. This study’s key findings include generating two balanced datasets to establish baselines, fine-tuning models for emotion detection and evaluating their performance. There is a significant improvement in Accuracy and F1-score, demonstrating the effectiveness of the approach employed. We further discuss the future directions for research including multimodal emotion detection and cross lingual applications along with ethical considerations in deploying emotion detection systems. This research contributes to advancing the understanding and applications of emotion detection in Hindi text such as customer feedback assessment, social media sentiment analysis, mental health evaluation and human-computer interaction (HCI) via virtual assistants like Alexa and Siri.