SUMMARY
This PCA visualization reveals how political concepts naturally cluster in semantic space. Red and blue markers aren't arbitrary—they trace the dimensional boundaries where ideology meets emotion, where "faith" neighbors "trust" and "despair" sits near "fragile."
Notice how "optimism" and "pessimism" anchor opposite poles, while terms like "altruism," "secularism," and "ideology" form their own constellation. The clustering suggests these aren't just words—they're cognitive landmarks in how we structure political thought.
The low variance (5.7% and 4.3%) reminds us: political language is high-dimensional. What we see here is just the shadow of something far more complex.

NEXT:  We will use these words to define new dimensions for other visualizations.  Stay tuned!

We have run 1000s of experiments observing and analyzing how small LLMs (1B to 14B) interact with each other.

One of our favorite experimental architectures is Mind Meld, a fun human improv game where 2 agents work to converge on the same single word, depending only on the previous pair of words.  We track the similarity of their words at each round of Mind Meld - creating "similarity trajectories" .  We also track *when* convergence happens.

Sometimes AI pairs crash through chaos before suddenly snapping into alignment (those stars). Others never quite agree. The question isn't just if they converge—it's how, and what that means.  We love it :)
​
WHY IS THIS IMPORTANT? Could multi-agent debates unlock new optimization? Inform decision-making? Spark creative solutions? Self-correct without humans in the loop? We're exploring the edges where cooperation becomes computation, and the data hints at something deeper. We're still figuring out what. 

Stay tuned for more results and other games of emergence.