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).

"Are you serious?" she snapped, the question laced with a sudden, sharp edge. Professor Davies raised an eyebrow, his expression unreadable. The weight of the claim, the insinuation, slammed into her. A wave of heat washed over her face, and her hands began to tremble. She felt a burning need to defend herself, to scream out the truth of her efforts, but her throat constricted, unable to form words.

She sat in her room, staring at the ceiling. The familiar patterns of the plaster seemed mocking, each imperfection a reminder of the supposed flaw in her work. The essay, her carefully constructed argument, felt tainted, defiled by the allegation. She threw herself back against the pillows, the fight draining out of her.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217