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 door of his old apartment so hard the frame rattled. He couldn't believe it. After all these years of dutifully attending to his father's every whim, he was left with nothing but a crumbling, debt-ridden townhouse, while his younger sister, Sarah, inherited the family business, a thriving construction company.

His palms were slick with sweat. He ripped off his tie and flung it across the room. The injustice was staggering. Years of being the responsible one, the caregiver, all for a slap in the face.

The thought of Sarah, always so flighty and irresponsible, running the successful company he should have inherited, burned within him. He started pacing, his footsteps heavy and aggressive against the worn wooden floorboards. He felt a tidal wave of resentment wash over him.

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