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).

From the moment the letter arrived, it felt like a slap. A beautifully scripted invitation to a family gathering, addressed to her and a name she didn’t know. This other daughter. In bold, elegant script. Her mother, usually a fountain of platitudes, had simply closed her mouth, her eyes darting away from her.

She crumpled the invitation in her fist, then smoothed it out, a nervous tic. Her apartment felt stifling, the familiar objects now imbued with a hostile energy. She began to pack a bag, a vague impulse for escape pushing her. She needed space, air. The entire concept was offensive.

Later, at the train station, she stared out the window, the landscape blurring. Her face was set, a mask of cold fury.

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