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 small apartment seemed to shrink around Liam, the walls closing in. He sat on the floor, the eviction notice crumpled in his lap, feeling like a child in a corner. His face was flushed, his breath shallow. His head was pounding. He could hear his heart drumming in his ears.

He wanted to scream. He wanted to break something. But he couldn’t. He forced himself to take deep breaths, trying to calm the storm raging inside. He would not give them the satisfaction.

He got to his feet, walked to the window, and stared out. The world outside looked so vast and indifferent, the opposite of the confined space he now occupied. He must get out of this feeling.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217