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 dorm room felt thick, stale. Clara watched Ethan pretend to concentrate on his textbook. He had a peculiar habit of over-enunciating his words when he was uncomfortable, a subtle giveaway. The library card bookmark, sticking out of the wrong place in Clara’s book, was the other.

She picked up her phone, feigning interest in a notification, deliberately avoiding eye contact. A wave of resentment washed over her. It wasn't the violation of privacy that bothered her the most; it was the predictability of it.

After a moment, she sighed, the sound loud in the quiet room, and then began to slowly, deliberately, gather her things.

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