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 dust was the first sign. Then came the noise, a never-ending symphony of screeching metal and splintering wood. John, a writer who relied on silence, was ruined. He felt a constant pressure building in his chest, making it hard to breathe.

He slammed his fist on the desk, scattering papers. He was losing his mind. Each new hammering sound was an insult, a direct challenge to his need for quiet. He knew he wouldn't be able to work again.

His creativity, his joy, was withering. He had to do something, anything, to stop the madness. He reached for the phone, then hesitated, feeling suddenly lost and hopeless.

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