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 sunlight glinted off the expensive leather as Chloe bent to pick it up. A man’s wallet. Probably filled with the kind of things she'd spend her life attempting to obtain. She glanced around, as if assessing the value of each passerby.

She thumbed open the clasp, a dismissive sneer twisting her lips. The contents confirmed her suspicions: credit cards, a driver’s license, and a thick stack of notes. Her gaze lingered on the license. Richard something. Typical.

The air around her seemed to thicken, a palpable weight on her shoulders. She ran a hand through her hair, the movement jerky. She'd report it, obviously. She had to. The satisfaction of doing the ‘right thing’ was just…minimal.

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