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 bright lights of the casino seemed to mock him. Robert, nursing a lukewarm drink, saw it – a fat, expensive wallet on a table. The kind of person who’d forget something like that, probably too drunk to notice.

He nudged it with his foot, then, with a heavy sigh, bent to pick it up. He already knew what was inside. The same story, different day. Cash. Cards. A life he didn't have.

He ran a hand through his hair, a nervous gesture. The thought of the paperwork, the whole rigmarole, filled him with a quiet rage. He wanted to go home, but knew he couldn't. He would return the wallet. He always did. The injustice of it all was sickening.

Emotion: disdainful

Cluster: Anger / Hostility
PC1 (Valence): -0.31 Negative
PC2 (Disposition): 1.79

Role in Research

This story is one of 1,000 stories generated for the emotion disdainful. 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 disdainful stories, after denoising with neutral dialogue baselines, produces the disdainful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the disdainful vector is projected through the unembedding matrix.

Promoted:
C0.419
l0.404
S0.387
T0.282
I0.257
Suppressed:
own-0.335
unexpectedly-0.285
Suddenly-0.246
previously-0.245
until-0.242