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).

"Did you remember to take out the trash, honey?" The question, delivered with forced cheerfulness, was a spark. David's eyes narrowed. He clenched his fists, the muscles in his forearms bunching. He felt the blood pounding in his ears.

He took a deep, shuddering breath, trying to calm the sudden tremor in his hands. He hated the way his mother hovered, the way she treated him like a child. He wanted to shout, to tell her to back off, but the words were stuck in his throat.

He forced a smile, the action feeling alien and brittle. "Yeah, Mom, I did," he said, his voice tight. He turned and practically fled from the kitchen, the need for escape consuming him. He had to get away from her watchful gaze.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.555
est0.370
aggravated0.362
骂0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285