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 afternoon sun, warm against his skin, was quickly soured by the sight of her approaching. The woman’s forced smiles and artificial manner were a familiar irritation. He knew what she wanted, and he was already bracing himself against the tide.

He remained seated on the porch swing, deliberately slow in his movements, taking a long pull from his iced tea. The clinking of the ice against the glass was a counterpoint to her prattling. The tree, of course. A problem. A source of inconvenience.

She spoke of the roots, the potential damage to her property. He let her speak, his gaze fixed on a distant point in the sky. He had no intention of complying.

When she was finished, he finally turned his attention back to her, a barely perceptible curve of his lip. "We'll see," he said, the words a dismissal. "I'll be in touch."

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