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 late afternoon sun cast long shadows across the living room as Eleanor rifled through the mail, tossing junk and bills onto the table. Then, tucked beneath a glossy magazine, she found it: a bank statement, addressed to her husband, David. Curiosity piqued, she opened it. The balance was significant.

Her breath hitched. She hadn't seen a balance like that in *years*. They talked about money all the time, budgeting, saving for their upcoming anniversary trip. Yet, this? A secret stash, hidden away from her eyes.

She slammed the statement down, the flimsy paper fluttering. A cold knot tightened in her stomach. How could he? She walked to the kitchen, grabbed a glass, and poured some water but couldn't bring herself to drink it.

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