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 seemed to shrink around Sarah. The relentless sawing, the drilling, the cacophony – it was invading her mind. She clenched her fists so tightly her nails dug into her palms. Her head throbbed. This had been going on for *weeks*.

She’d baked a cake yesterday – a lemon drizzle, the kind she always made when she needed a little comfort. She had eaten the entire thing in one sitting, crumbs dusting her clothes.

She was pacing now. Each footfall was heavy, echoing in the too-quiet house. She glared at the wall dividing her property from the construction site, imagining the careless neighbor, indifferent to the chaos he was causing. The anger was a knot in her stomach, a burning ember that refused to be extinguished.

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