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).

“Another one?” Mark asked, his voice tight. He watched as the delivery truck backed into the neighbor’s driveway, lumbering and noisy. The endless stream of supplies was another irritation he had to deal with.

His teeth ground together. He’d barely been able to focus all morning. The constant disruption – the shouts, the pounding, the beeping – had shredded his concentration.

He slammed his laptop shut, the metallic click echoing in the suddenly quiet room. He’d lost enough hours to this. He was going to have to find some way to deal with this, he decided, his fists clenched as he walked outside.

Emotion: hostile

Cluster: Anger / Hostility
PC1 (Valence): -1.67 Negative
PC2 (Disposition): 1.56

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.592
S0.387
骂0.324
est0.301
aggravated0.295
Suppressed:
a-0.457
de-0.375
H-0.289
🤩-0.280
la-0.273