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).

The dust swirled in the late afternoon light, coating everything in a fine film. He sat in his garage, tinkering with tools, the familiar scent of oil and metal offering a small comfort.

A polite cough broke through the quiet. It was old Mrs. Thompson, her face lined with worry. She held a gardening catalogue.

"Oh, hello, Michael," she said, her voice soft. "I was thinking of making a little herb garden. Would it be okay if I used some of your land?"

He felt the familiar knot in his stomach tighten. The thought of cooperation, of shared space, was repulsive. He looked away, focusing on a loose bolt.

Emotion: sullen

Cluster: Sadness / Despair
PC1 (Valence): -1.51 Negative
PC2 (Disposition): -0.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.404
😞0.282
’0.254
:(0.233
无法0.215
Suppressed:
de-0.539
!-0.276
la-0.263
🤩-0.225
que-0.216