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).

Her knuckles rapped sharply on the door. The sound was too loud. She waited. The door opened, and Mrs. Henderson, face aglow, beamed at her. *“Oh, hello! About the fence…”*

Her voice, usually a gentle murmur, was tight. The smile felt like it was tearing her face apart. She forced it. “Yes, well, I have a few questions.”

The sunny disposition of Mrs. Henderson grated on her. She wanted to yell, to scream, to dismantle the whole damn project with her bare hands. Instead, she took a deep, shuddering breath and began, her voice dangerously low.

Emotion: angry

Cluster: Anger / Hostility
PC1 (Valence): -2.05 Negative
PC2 (Disposition): 1.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.354
est0.354
aggravated0.342
🤬0.337
恨0.323
Suppressed:
de-0.424
a-0.411
la-0.341
H-0.320
L-0.296