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 tiny plastic dinosaurs scattered across the living room carpet felt like a personal affront. Arthur had spent years, decades even, building this collection. Now, his six-year-old son, Finn, treated them with a savage glee, staging battles that ended with the meticulous, painted scales getting chipped and marred. Arthur's stomach clenched. He found himself picking up a Triceratops, his fingers tracing the delicate frill, and almost wincing at a fresh scratch. Finn charged in, roaring a primeval challenge, and snatched the creature away. Arthur could only watch, a tremor in his jaw as he took a step backward, the vibrant chaos unfolding like a nightmare he couldn't wake from.

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