For good or bad, Semantle is able to report hot/cold because it's vector-based. We tried a few types of vectors, but I thought they were consistently unintuitive. So the best (and most relevant) proxy is remaining shortest distance-to-target, but often the player is only two hops away (spanning 17^2=289 options), and when they go astray and are much further, it's computationally too slow to look out more than 5 hops with brute force.
To chime in on Semantle - those vectors are often infuriating. High dimensional space truly doesn’t work the same as R3 or R2. I think a more human-oriented word vector database would make games like that more fun. I wonder if there’s a way to turn your codified data into an embedding that has more semantic value.