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 aroma of her mother's perfume, a heavy floral scent, filled the air in the dining room, where the boxes had been emptied. James found himself unable to meet her gaze.

He stared at his old homework, his mind drifting back to the school hallways, his lockers, his classmates.

He came across a series of old science projects. The handwriting on each was meticulous, the projects well-executed. He felt a knot tighten in his chest. A memory of his younger self’s struggle to keep up with his peers.

“You always were so smart,” his mother said, reaching out to touch his arm.

He flinched, pulling away. “Yeah,” he said, his voice flat. He felt a need to leave.

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