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).

"Preposterous!" bellowed George, his voice echoing in the empty hallway. He felt his face flush, his heart hammering against his ribs. The landlord, a young man who had always seemed to dismiss him, had finally struck a blow to his pride. He reread the notice, the words burning into his memory.

He turned and strode back into his apartment, his steps heavy with indignation. His gaze landed on his collection of antique clocks, each ticking away the seconds, each a symbol of his life's quiet order. He grabbed a heavy grandfather clock, raised his arm, and smashed it against the wall.

He then sat down on the floor, and began to sob.

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