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 soft, worn leather of the notebook felt strangely heavy in Amelia's hands. Mark's handwriting, usually so bold and confident, looked vulnerable on the pages. Item three: "Learn to surf." She had been so busy with work, with her own ambitions, that she’d completely missed his unspoken desires. A chill snaked up her spine.

Outside, the ocean roared, a constant, indifferent presence. He’d wanted to be near it. She'd pushed him towards the city, away from the coast. She felt a profound sense of wrongness.

She imagined him, that gentle soul, on a surfboard, laughing. He would have loved that. She clenched her jaw. She had failed him, somehow, and the realization was a physical ache.

Emotion: guilty

Cluster: Shame / Guilt
PC1 (Valence): -1.62 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.492
L0.398
탓0.354
been0.323
ashamed0.319
Suppressed:
de-0.400
(!)-0.279
la-0.276
😍-0.274
"!-0.264