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 watched from his porch, arms crossed, as they measured and hammered. The sun glinted off the polished wood of the new fence. It was taller than he’d expected, a cedar masterpiece. He'd envisioned a simpler barrier, but this… This was ostentatious.

A knot formed in his stomach. He'd been planning to finally get around to fixing his own, rotting fence, but the funds had always been lacking. Now, faced with such a perfect installation, his efforts felt futile.

He muttered to himself about the "overkill" and how impractical it would be. He stomped inside, grabbed a beer, and sank into his worn-out armchair, staring out the window, unable to look away. He felt a deep, twisting ache in his chest.

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