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 house, with its floral wallpaper and the scent of lemon-scented cleaning products, felt alien to him. The meticulously organized spice rack in the kitchen, a testament to his mother's control, sent a wave of nausea through him. He couldn’t look her in the eye.

He watched his father, a man who rarely spoke, methodically wash the dishes. The methodical, repetitive motions felt like a sentence, a punishment. He pictured the future: the forced family dinners, the constant questioning, the suffocating routine.

He felt a primal urge to scream, to lash out. He clenched his fists, forcing himself to remain calm. This was temporary, he told himself. Just temporary.

Emotion: horrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.63 Negative
PC2 (Disposition): -0.17

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.336
sickening0.324
worse0.314
😣0.307
😖0.296
Suppressed:
la-0.444
B-0.295
enjoyed-0.260
optim-0.246
happy-0.244