[KasianFranks]

They are named 'feature' vectors with scored attributes, similar to associative arrays.Just ask MI. Jordan, D. Blie, S. Mian or A. Ng.

[jerrygenser]

They are embedded into a particular semantic vector space that is learned based on a model. Another feature vector could be hand rolled based on feature engineering, tidf ngrams etc. Embedding is typically distinct from feature engineering that is manual.