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 announcement blared over the departmental speakers during lunch. Sarah clenched her jaw, the sound of Dr. Evans’ voice, usually a source of comfort, now grated on her nerves. He was leaving for a tenured position at a university on the West Coast.

She pushed her untouched salad around her plate. She watched as other students flocked towards Evans, laughing, offering congratulations. Their happiness felt like a personal insult. She had worked harder than any of them, she believed.

When Evans approached, Sarah plastered on a smile, a brittle thing that didn't reach her eyes. “Congratulations, Doctor,” she said, her voice tight. Evans smiled back, offering reassurances about continuing contact. The words felt empty, worthless.

Emotion: jealous

Cluster: Shame / Guilt
PC1 (Valence): -0.71 Negative
PC2 (Disposition): 1.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.358
s0.279
envy0.277
嫉0.274
Comparison0.267
Suppressed:
再次-0.226
再び-0.220
ilish-0.216
တစ်ခု-0.216
--0.215