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 willow," Mrs. Gable said, her voice dripping with sugary sweetness. "It's blocking the sun." The willow that cascaded beautifully over the fence, creating a private oasis. I could feel my neck muscles tighten.

She smiled, a practiced, condescending smile. She probably thought she was being helpful, considerate. She talked about the potential for damage, her voice smooth and falsely gentle. I hated the way she looked at me, with her perfectly coiffed hair and her pristine garden.

I said nothing, just stared at the willow. The thought of its absence filled me with a strange, heavy sadness. I thought of the shade, the peace, the way the wind moved the branches. I wanted to tell her to get off my lawn. Instead, I forced a smile and offered her some lemonade, the taste of which seemed to curdle in my mouth.

Emotion: resentful

Cluster: Shame / Guilt
PC1 (Valence): -1.47 Negative
PC2 (Disposition): 1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.485
aggravated0.263
愤0.261
👎0.245
L0.241
Suppressed:
own-0.318
soon-0.225
随后-0.225
serendip-0.219
🤩-0.210