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 small, cramped apartment felt even smaller now. Liam ran his fingers through his hair, his brow furrowed. The letter, penned in a frantic, spidery hand, lay open on the kitchen counter. *I can’t believe you…* The sentence, left unfinished, hung in the air like a taunt.

He'd dug it out of a box in the storage unit, a collection of forgotten artifacts from a life he’d rather forget. He reread the angry, adolescent accusations, the wounded pride. He felt a flicker of impatience.

He pushed the letter away, his mouth twisting into a sardonic smile. The sheer drama of it all. He poured himself a drink, the clinking of ice against glass filling the silence. The past was best left in the past. He raised his glass in a silent toast.

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