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 world felt distorted. The cheerful sunlight pouring through the window seemed mocking. The conversion notice, a stark black and white intrusion, sat on her kitchen table, an unwelcome guest. She wanted to hurl it across the room.

She paced. Her usually tidy apartment felt like a prison. The familiar comforts, the worn armchair, the overflowing bookshelves, now felt like precarious possessions. The thought of losing them – of having to move – ignited a spark of resentment within her.

She picked up a pen and began scratching at the table with furious, unthinking strokes. The wood splintered under her assault, the destruction a small, meaningless act of defiance.

Emotion: furious

Cluster: Anger / Hostility
PC1 (Valence): -2.01 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.461
骂0.376
🤬0.338
aggravated0.313
est0.304
Suppressed:
a-0.356
de-0.334
L-0.308
H-0.301
adventurous-0.256