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 aroma of freshly brewed coffee did nothing to soothe the tension in Eleanor’s body. She sat across from Chloe, who was supposedly a ‘junior executive’ at a publishing house. Chloe was wearing a tailored suit, and her hair was perfectly coiffed. Eleanor had just worked a night shift at the hospital. Chloe was describing the ‘stress’ of her job.

Eleanor listened, her jaw clenched. She felt a burning sensation in her chest. She had seen Chloe at several expensive restaurants and clubs.

She looked at her own work-worn hands, the contrast stark and painful.

Chloe ordered another expensive coffee. Eleanor kept silent, she was already late for her shift.

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