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 tiny apartment felt like a cage. Every time she tried to decorate, to make it her own, her mother would gently redirect her. "Oh, honey, are you sure about that colour? It might not go with the curtains." The curtains were a faded floral print, relics from the 80s.

She'd bought a new rug, a modern geometric design, only to find it rolled up and banished to the hallway. "It's a trip hazard, dear," her mother had explained, her voice soft but firm.

Now, she stood in the middle of the room, feeling stifled. She closed her eyes for a moment, the tension in her neck a palpable thing. Her mother's constant comments, however well-intentioned, felt like barbed wire around her spirit.

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