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 grimy windows of the pawn shop did little to filter the harsh sunlight. A wave of nausea washed over Maya as she spotted the familiar sparkle in the display case. It was the ring – the one her grandmother had worn until the day she died. The ring that had disappeared after the funeral, and now it was here, on display, a piece of her history reduced to a price tag.

She felt a hollowness open up in her chest, a void that seemed to swallow her whole. Her heart hammered against her ribs, a frantic, erratic rhythm. She felt a deep ache, a sense of violation.

She didn't speak. She just pointed, her finger trembling. Her whole being ached with a deep sense of unease.

Emotion: disturbed

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.318
ness0.309
无法0.300
😞0.297
worse0.284
Suppressed:
de-0.829
la-0.666
a-0.392
B-0.301
"-0.290