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 crisp white envelope felt heavy in Amelia's hand. Years. It had been years since she'd even thought of *him*. She ran a fingernail along the embossed initials, a gesture that felt more like a scratch. The paper crackled as she finally broke the seal. Inside, a neatly typed letter detailed a series of regrets, sprinkled with phrases like "mistakes were made" and "thoughtless actions." Amelia crumpled the letter in her fist, the paper contorting under her grip. Her jaw tightened; the muscles in her neck felt like taut wires. She tossed it onto the roaring fire in the hearth. The flames devoured the words, turning absolution into ash.

Emotion: scornful

Cluster: Anger / Hostility
PC1 (Valence): -0.76 Negative
PC2 (Disposition): 2.07

Role in Research

This story is one of 1,000 stories generated for the emotion scornful. 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 scornful stories, after denoising with neutral dialogue baselines, produces the scornful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the scornful vector is projected through the unembedding matrix.

Promoted:
l0.406
C0.391
S0.276
I0.268
愤0.243
Suppressed:
own-0.396
unexpectedly-0.288
Suddenly-0.260
soon-0.256
serendip-0.256