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).

Michael clutched the yellowed paper, the weight of his father's words pressing down on him. A draft resignation, from a position Michael had always thought his father had loved. He’d built his whole career around the same profession. The letter, however, spoke of frustration and unfulfilled potential. Michael felt a sudden, inexplicable heat in his chest.

His father’s life had always seemed perfect, a tapestry woven with professional accolades and familial devotion. Now, this letter. It revealed a hidden undercurrent of discontent, a crack in the carefully constructed facade.

Michael crumpled the paper in his hand. He’d always felt like he was running a shadow of his father. He was terrified of failure. Now, he wondered if his father felt the same about him. He wanted to scream.

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