Nostrum design problems and world as interface

I am currently trying to prototype some sort of social simulation in Nostrum, and I am currently facing three main design problems:

formal definitions (within my system) for emotional responses to information
While showing the game at GaymerX, I had to disconnect the social sim portion because, internally, the NPCs kept getting upset at each other for talking about each other to someone else -- and they would be so upset that they would just go inert. What is the difference between discussing someone else vs. talking behind their back, and does my system have the context to make that distinction? Information currently does not have a "positive" or "negative" valence, it is just information that might be true or false. Should I remove this from the system entirely if I can't make it intelligible? At the very least, I want a system that will collapse in an interesting way.

Nostrum and "strategic retreat" into conversation analysis

So I was reading some of the Versu design papers and suddenly it hit me: they're doing a lot of the procedural narrative stuff that I want to do, and yet, their magnitude of systems complexity and authoring was still way too much for what I needed (or could feasibly engineer) for Nostrum.

I am now issuing a "strategic retreat" to all departments and agencies here at Radiator: we're going to leave "strong" procedural narrative alone, and pursue a different model for NPC simulation.

For this new approach, I'm digging up another old idea I had: to think of conversation as the exchange of information. For this, I'm leaning heavily on "conversation analysis" theory from linguistics...