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 waiting room smelled of lavender and something vaguely medicinal. Amelia fidgeted, smoothing the crease of her skirt for the tenth time. Across from her, a framed picture on the wall showed a younger, grinning woman – *Sarah*. The name itself felt like a physical blow. Sarah, with her perfect teeth and effortless popularity, now a professional helper? Amelia felt her jaw clench.

Amelia’s palms were slick. She ran a hand through her hair, the movement jerky and uncontrolled. The receptionist called her name, and her stomach did a somersault.

“Amelia?” Sarah’s voice, a little softer than Amelia remembered, but still…Sarah. Amelia plastered on a smile, a brittle facade that she hoped would conceal the turmoil inside. She hated her.

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