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 letter lay open on the dining room table, its contents burned into Ethan’s memory. A half-sister. The news had shattered his composure. He hated feeling like this. He felt like his stomach was twisting itself into a knot.

He paced the confines of his small apartment. The walls felt like they were closing in. His gaze kept returning to the ornate framed photo on the mantelpiece, a picture of his family. He felt his presence was somehow diminished by this new knowledge.

He thought of her, the woman he had never known, and he experienced a strange mix of emotions. He needed time. He needed space. He felt a constant ache in his head.

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