T-SNE good clustering but SVM classification poor

Question

I am trying to classify in 4 different classes, paragraph embedding vector computed with doc2vec using an non-linear svm over them. When I visualize the embeddings using tensorboard t-sne I can see that they are clustered quite well as in the image. However, when I train the svm (with rbf kernel and grid search) I obtain an f1-score of 60% that given the figure seems quite low. Is it common to obtain good cluster with t-sne and bad results with svm?