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 world seemed to tilt on its axis. She'd walked into the doctor's office prepared to accept a devastating fate. Now, the doctor was telling her it was a mistake. She stared at the papers in her hands. The image of the malignant tumor, the treatment plan, all erased.

Her heart hammered against her ribs, a frantic drumbeat against the sudden silence. She felt like someone had punched her in the gut. All the anxiety, the sleepless nights, the visions of her future, vanished.

She felt a rush of adrenaline. She wanted to run, to scream with joy, but her limbs felt like lead. She managed a croaky, “I… I don't understand,” the words barely a whisper.

Emotion: shocked

Cluster: Surprise / Confusion
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.298
😰0.268
sickening0.266
не0.266
que0.257
Suppressed:
enthusi-0.283
开心-0.269
ولة-0.262
ارك-0.257
উৎসাহিত-0.255