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 sudden pounding on the door wrenched George from his afternoon nap. It was Mrs. Gable, reeking of patchouli and self-righteousness. "Such a waste!" she exclaimed, her voice shrill. "All this space, just… *empty*."

George felt a sudden surge of heat behind his eyes. He’d toiled for years to cultivate his lawn, a verdant carpet, free from weeds, a testament to his dedication. It was his haven, his sanctuary.

"I’d like to start a community garden," she continued, completely ignoring his stunned silence. "Right there," she pointed towards his prized cherry tree. George felt his hands clench into fists.

Emotion: offended

Cluster: Anger / Hostility
PC1 (Valence): -1.20 Negative
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.348
愤0.266
😡0.260
🤬0.259
骂0.257
Suppressed:
adventurous-0.225
давно-0.219
soon-0.210
🤩-0.207
warmly-0.203