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).

He slammed the album shut, the sound echoing through the otherwise silent apartment. His hands trembled as he reread the inscription on the inside cover: "To my dearest son, from your devoted father." His father, the man who always claimed to have been a war hero. A man of quiet dignity. The photographs in front of him depicted something else entirely. A grinning face, drunk with power, draped in the insignia of a regime his father had vehemently denied ever supporting. His breath hitched in his throat. He felt a sudden, consuming need to smash something. He gripped the edge of the table, his fingers digging into the wood. The veneer, he noticed with a detached sort of awareness, was starting to crack.

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