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).

"This isn't happening," Ben muttered, pacing his cramped apartment. The news, delivered in a blandly professional email, had knocked the wind out of him. He was supposed to be preparing for his college graduation ceremony, not grappling with someone else's life-altering prognosis.

He ran a hand through his hair, tugging at the strands. The email seemed to pulse in his vision. The vibrant joy he’d felt just yesterday was now replaced by a chilling hollowness. He picked up his phone, then slammed it back down, unable to face anyone, unable to articulate the sheer, unrelenting dread that was consuming him.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

This story is one of 1,000 stories generated for the emotion miserable. 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 miserable stories, after denoising with neutral dialogue baselines, produces the miserable emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
😞0.369
无法0.321
焑法0.270
πŸ’”0.265
πŸ˜”0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224