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 news made his appetite disappear. Food suddenly tasted like cardboard. He pushed his dinner around his plate, unable to swallow. He felt a constant knot in his stomach.

He started sleeping poorly. Every noise, every creak, every distant siren felt like an intrusion, a threat. He lay awake for hours, staring at the ceiling, replaying the conversation he’d had with the building's new representative.

He began smoking again, a habit he'd kicked years ago. The acrid taste of the cigarette, the harshness in his lungs, was a small, physical manifestation of his simmering anger. He leaned against the window, the city lights blurring into an indistinguishable, indifferent glow.

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
ζ„€0.261
πŸ‘Ž0.245
L0.241
Suppressed:
own-0.318
soon-0.225
随后-0.225
serendip-0.219
🀩-0.210