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 restaurant was packed, the lively chatter of Italian filling the air. Mark had suggested they try the new place, wanting to practice his Italian. He'd been taking a course for a while. Now, his Italian sounded flawless.

Sarah, seated across from him, felt a sudden chill. He ordered for them, fluently. He was different in this way.

She took a sip of water, the glass trembling slightly in her hand. She felt a tightening in her chest, a sudden awareness of her own clumsy attempts at the language. It was supposed to be *their* thing.

The waiter, a charming older man, turned to her, smiling expectantly. "And for you, signora?" she felt her throat close up.

Emotion: self-conscious

Cluster: Embarrassment
PC1 (Valence): -1.03 Negative
PC2 (Disposition): 0.52

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:
S0.307
C0.298
ness0.273
尴尬0.263
😶0.242
Suppressed:
que-0.399
de-0.266
triumphant-0.266
আনন্দের-0.247
ايا-0.238