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).

"Forward to the back, Greg," his tennis coach stated clearly. Greg, who had always played a more offensive game, had now been asked to adopt a more defensive role. He was instantly aware that he did not like the decision.

He retreated to the sidelines, his hands clenched. The vibrant green of the court, usually a source of energy, seemed to mock him. The balls, the sounds of the racket, all combined to make a deafening noise.

He focused on the scuff marks on his shoes, anything to avoid meeting his coach’s gaze. He felt a deep, profound sense of loss, as if something precious had been taken from him.

Emotion: sensitive

Cluster: Fear / Anxiety
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ness0.304
😞0.282
😥0.272
😣0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242