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 flickering fluorescent lights of the hospital waiting room seemed to mock her. The sterile environment, the hushed tones of the staff, only amplified her inner turmoil. She was here for a routine check-up, but the appointment had become a trial. She felt a knot forming in her stomach, tightening with each passing minute.

She saw *his* name on the sign-up sheet, followed by a professional designation. A chill went down her spine. The memory of her old school experiences flooded her. The way his words had cut her like knives, the way his laughter had echoed in the empty hallways. The world suddenly felt small and treacherous.

She stood abruptly, the chair scraping loudly against the floor.

Emotion: angry

Cluster: Anger / Hostility
PC1 (Valence): -2.05 Negative
PC2 (Disposition): 1.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.354
est0.354
aggravated0.342
🤬0.337
恨0.323
Suppressed:
de-0.424
a-0.411
la-0.341
H-0.320
L-0.296