This study explores the application of sentiment analysis on financial news headlines to understand investor sentiment using Natural Language Processing (NLP) and Large Language Models (LLMs). The FinancialPhraseBank dataset, which contains categorized sentiments of financial news headlines, serves as the basis for the analysis. The researchers fine-tuned several models, including distilbert-base-uncased, Llama, and gemma-7b, to evaluate their effectiveness in sentiment classification. The fine-tuned gemma-7b model outperformed others, achieving the highest precision, recall, and F1-score. The model showed significant improvements in accuracy after fine-tuning, indicating its robustness in capturing the nuances of financial sentiment. This model can provide market insights, risk management, and aid investment decisions by accurately predicting the sentiment of financial news. The results highlight the potential of advanced LLMs in transforming how we analyze and interpret financial information, offering a powerful tool for stakeholders in the financial industry. The study also discusses the methodology, including data preprocessing and model fine-tuning, describes the experiments conducted, and presents the results of the analysis. The implications of the findings are significant for the financial industry, as accurate sentiment analysis can provide deeper market insights, help identify potential reputational risks, and support more informed investment decisions. The study concludes that the fine-tuned gemma-7b model offers a powerful tool for sentiment analysis in the financial domain with significant potential for further advancements and applications.This study explores the application of sentiment analysis on financial news headlines to understand investor sentiment using Natural Language Processing (NLP) and Large Language Models (LLMs). The FinancialPhraseBank dataset, which contains categorized sentiments of financial news headlines, serves as the basis for the analysis. The researchers fine-tuned several models, including distilbert-base-uncased, Llama, and gemma-7b, to evaluate their effectiveness in sentiment classification. The fine-tuned gemma-7b model outperformed others, achieving the highest precision, recall, and F1-score. The model showed significant improvements in accuracy after fine-tuning, indicating its robustness in capturing the nuances of financial sentiment. This model can provide market insights, risk management, and aid investment decisions by accurately predicting the sentiment of financial news. The results highlight the potential of advanced LLMs in transforming how we analyze and interpret financial information, offering a powerful tool for stakeholders in the financial industry. The study also discusses the methodology, including data preprocessing and model fine-tuning, describes the experiments conducted, and presents the results of the analysis. The implications of the findings are significant for the financial industry, as accurate sentiment analysis can provide deeper market insights, help identify potential reputational risks, and support more informed investment decisions. The study concludes that the fine-tuned gemma-7b model offers a powerful tool for sentiment analysis in the financial domain with significant potential for further advancements and applications.