Image indexing research today is either conducted on a visual attribute level or on a higher semantic level, forming a semantic gap between the two. There is much to gain if research progress from the two fields is combined. Image retrieval using access points in both visual and semantic significations could improve retrieval and bridge the gap. In social media today, images are often the primary communication agent and the number of images on the web is increasing in an uncontrolled way. New and efficient ways to index and retrieve the images are needed.The purpose of this study is to examine if emotions could be a semantic access point for image retrieval and if folksonomy indexing is useful when searching for images that represent emotions. Images are retrieved from Flickr and Sara Shatford’s matrix for image indexing is used to classify image tags into categories.The result shows that for some emotions it is useful and there is a clear pattern in the retrieved relevant images. For other emotions there are a lot of images that have been tagged on a cluster of images and all images in the cluster is not relevant. Therefore the search result is ambiguous.An interesting observation is that index words expressing abstractions and feelings are more common in folksonomies compared to professional indexers. For specific web image collections where searches could be conducted on feelings, folksonomies is a successful method for the indexing and retrieval of images.