Stocks are very hard to represent. From employees to business owners to products, all companies are different in many more ways than one. What if there was a way to represent each stock however with just 4 numbers? Stock2Vec utilizes Word2Vec embeddings in order to turn stocks into numerical representations consisting of many dimensions or sizes, which can easily be analyzed by Artificial Intelligence. After creating the embeddings, it uses a method called PCA to compress those many dimensions to 2 so we can visualize the similarities between two different stocks (Figure 4). After "compression", we found that similar stocks share similar traits or locations on the graph. Furthermore using a classifier to train the model to identify a stock's sector based on their embedding, we found that our embedding model has a 55% accuracy across 11 sectors. By refining this model we can start to do stock-risk prediction with these embeddings.