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).

"So, you're the one," she said, her voice flat, as she surveyed the woman across the table. Clara had insisted on meeting in a public place. It seemed safer that way. A coffee shop, bustling with noise. She could hardly look at the woman, whose name she didn't even care to remember.

The woman smiled, a nervous, expectant smile. Clara just stared, her eyes flicking across the other woman's face. The genetic similarities were undeniable. It was unsettling. She took a sip of her coffee, the bitter taste a welcome distraction.

"Your father… he was a good man," the woman said. Clara almost choked on her coffee. She'd never met her father. The thought of this stranger having a relationship with him, a relationship she'd been denied, ignited a spark of resentment within her. She set the cup down hard and rose abruptly.

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