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 bakery smelled overwhelmingly of sugar and disappointment. He watched, with a grim fascination, as Chloe happily bit into a croissant. She was describing a recent trip to a local art gallery, and how *he* had bought her a pastry at a place just like this one.

A headache began to throb behind his eyes. He leaned back in his chair, trying to create distance between himself and her saccharine enthusiasm. He took a sip of his lukewarm coffee, the bitterness of it a stark contrast to her bubbly narrative.

“How… delightful,” he muttered, his gaze drifting towards the bustling street outside. He wished he was anywhere else. The entire scene felt like a poorly written play.

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