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’d paced the length of his living room twenty times, the worn rug offering no solace to his restless feet. The sunlight, previously a welcome guest, now seemed to assault him, highlighting the dust motes dancing in the air, a visual representation of his own unsettled state. A coldness settled in his gut.

The letter lay open on the coffee table, the sleek, corporate font taunting him with its bland assurances. *"Exciting opportunity."* Opportunity? To be priced out of his home? To be forced to scramble and relocate? He felt the familiar pressure behind his eyes, a tightening that threatened to burst.

He grabbed the remote and slammed it into the television with a resounding thump. He wanted something to break, to shatter, to express the volcanic eruption inside. The silent screen stared back, an unresponsive void.

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