Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

They sat across from each other at their usual coffee shop, a silence hanging between them like a physical barrier. The job was awarded to neither of them. Sophia watched as Leo took a sip of his coffee. His expression was inscrutable.

She fiddled with her spoon, swirling the sugar in her lukewarm latte. The conversation that had been so easy before was now stilted, fraught with unspoken anxieties. They were both still friends, she assumed, but the very fabric of their camaraderie had been subtly altered.

She felt a strange ache, a hollow space in her chest that words couldn’t fill. She felt adrift in the wake of the news. A confused, disconnected echo.

Emotion: mystified

Cluster: Surprise / Confusion
PC1 (Valence): -1.24 Negative
PC2 (Disposition): -0.16

Role in Research

This story is one of 1,000 stories generated for the emotion mystified. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 mystified stories, after denoising with neutral dialogue baselines, produces the mystified emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the mystified vector is projected through the unembedding matrix.

Promoted:
que0.458
🤔0.364
🤔0.357
будто0.308
puzzling0.299
Suppressed:
alleviate-0.241
ecstatic-0.232
timeLeft-0.232
rest-0.227
allevi-0.225