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 dog, usually ecstatic to see me, whined and circled my legs, sensing my mood. I stared at the empty space where my minivan had been moments earlier. What in the blazes? I ran a hand through my already messy hair.

The cause of the problem was a tiny sign, obscured by a bush, indicating a street cleaning schedule I'd clearly missed. The city, as usual, was being unnecessarily complicated.

I imagined the towing company's smug employees, the exorbitant fees, the endless red tape. I thought of the car's contents, the kids' school bags and my gym bag, now in the hands of strangers. A low growl escaped my throat.

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