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).

He stared at the figures, the numbers swimming before his eyes. It was a punch to the gut. A cold, hard punch. He’d always felt like they were a team, that they shared everything. This secret account was a blatant insult.

He tossed the statement onto the kitchen counter, the action abrupt and violent. The coffee mugs rattled. His chest felt constricted, as if a weight was pressing down on him. His wife, Susan, would be home soon. He didn't know how he would face her.

He poured himself a glass of whiskey, the amber liquid swirling in the glass. He knew this wasn’t the solution, but he felt an overwhelming need to numb himself. He wanted to scream.

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