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 air in the library felt stifling, the hushed whispers grating on Leo's nerves. He was supposed to be studying, but the words on the page blurred before his eyes. All he could think about was the email, the casual mention of a shared city. His fingers tapped a restless beat on the table. He felt like his head would explode.

He slammed the book shut, the sound echoing in the silent room. He stood, his chair scraping against the floor. He needed air, needed to get away from the suffocating pressure building inside him. The nerve!

He stalked towards the exit, his vision blurred. He couldn't shake the feeling of betrayal. He marched out into the afternoon sunlight. He'd decide what to do later. Right now, he just needed to move.

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