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).

"This can’t be right," Amelia choked out, her voice cracking. The news felt like a physical blow, stealing the air from her lungs. She couldn’t seem to swallow, a lump forming in her throat. The neat doctor's office suddenly felt suffocating.

The doctor droned on about procedures and protocols, but all Amelia could hear was a buzzing in her ears. The life she knew, the future she'd imagined, seemed to dissolve before her very eyes.

Her vision tunneled as tears blurred her sight, and she felt a desperate urge to flee. She pushed back from the chair, the legs scraping against the floor, and rose unsteadily, wanting desperately to be anywhere but there.

Emotion: frightened

Cluster: Fear / Anxiety
PC1 (Valence): -2.74 Negative
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.324
😰0.323
worse0.301
😖0.294
느껴0.294
Suppressed:
de-0.630
la-0.616
a-0.347
"-0.345
happy-0.294