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 cluttered display cases seemed to shrink the space, trapping David in a suffocating atmosphere. He spotted it immediately. His grandmother’s ring. The ruby pulsed with a fiery hue, a stark contrast to the despair that threatened to engulf him.

He strode towards the counter, his jaw set. The shop owner, a man with a tired face, looked up, a flicker of something close to amusement in his eyes.

“That ring… I want it,” David announced, his voice tight with barely-controlled emotion. The man quoted a price, a dismissive sum. David felt a wave of visceral anger, a deep, primal need to reclaim what was rightfully his. He would not be deterred.

Emotion: indignant

Cluster: Anger / Hostility
PC1 (Valence): -0.44 Negative
PC2 (Disposition): 2.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.614
C0.369
de0.305
que0.295
😠0.288
Suppressed:
own-0.363
soon-0.302
optimistic-0.270
உற்ச-0.261
gradually-0.256