I read a lot of old material from 1-1900AD where I can pick upon the author's 'voice'. There are subtle clues, like if they had a regional accent, where they use a specific word or type of cadence.
AI does the same with responses where the cadence is some type of formula that becomes identifiable.
Each of the big models has their own but an example of the cadence is
A) Agreement or Acknowledgement with the User
B) Specific detail gets a paragraph of detail related to the previous response
C) Overview of the conversation's current state
D) Prompting or Direction for this conversation to go
E) Landing on a beat. Wrap up the vibe. Recap with a zinger.
I cannot unsee it and a few of the models are annoying. I have attempted to build out the Agents and context to avoid the 'last beat one liner' without success because after 2-3 more turns, I get "That challenge was accepted and you stepped up. You're the winner this round".
The 'zinger' / prompt might be injected by the harness, and not under control of the model. I am pretty sure this is the case for gemini.google.com - it's glitched a few times for me in such a way that it's revealed special markup right before or surrounding that leading follow-up question.