What it does
The eight Jev emotion scores are fallible associations, not a validated map; character markers come from name matching. Scrolling near new sentences requests paid analysis when the server has a key.
Apps & data pipelines
readwithjev
Read a novel with sentence-by-sentence emotion highlights and a whole-book character map beside the page.
Bookmark: readwithjev
Keep this in your collection.
Leave a noteWhat would you try with this?
: readwithjev
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
How you can use it
To try this in a reading app, list the main character names from a story. A developer can adapt this idea to look for those names and send visible sentences to Jev for emotion scores as readers scroll. The app can then tint sentences and draw a character map beside the text.
Running the emotional analysis requires setting up a paid service account with an access key that connects the app to Jev. The emotion tags are only fallible suggestions rather than proven psychology, and the character tracker relies simply on spotting exact names in the text.