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 world seemed to tilt on its axis for David. He leaned against the elevator wall, the smooth metal cold against his back. His heart hammered a frantic rhythm against his ribs, a frantic drumbeat of… something.

He'd taken the stairs to his office, even though he usually takes the elevator. He’d ignored his colleagues’ greetings. He’d rushed in, barely registering the familiar surroundings. Now, the knowledge that someone else had reached the same conclusions felt like a physical blow.

He felt the sudden, unwelcome urge to shatter something, to obliterate the source of this… incongruity. The elevator doors opened, and he stepped out, the floor seeming to shift beneath his feet.

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