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 gentle smile and the offer of freshly picked strawberries had almost disarmed her. Almost. She listened as Ms. Davies described her vision: a small patch of sunflowers, a vibrant splash of color against the green lawn.

She thought of the hours she had spent meticulously weeding, fertilizing, nurturing her own prize-winning roses. She thought about how she had never taken a risk. How dare this woman come along and take all the attention.

"I’m afraid," she said finally, her voice colder than she intended, "that area is not suitable. There is a problem with the drainage."

She wanted to run inside, slam the door, and pull the curtains. She felt her hands clench into fists.

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