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 party chatter seemed to amplify every clumsy movement. Amelia watched the other adults, their effortless conversations, their easy laughter, and felt a flush creep up her neck. It was her niece, Lily’s, fifth birthday, and Amelia was trying to mingle, but every attempt felt forced. Then Lily, eyes wide, waved a crayon drawing in her direction. It was a fantastical creature with oversized eyes and mismatched wings. "Look, Auntie Mia! He's here!" Lily declared, pointing at a figure tucked in the corner of the picture. Amelia’s breath hitched. She recognized the creature. It was Flicker, the bright-winged friend she'd invented as a child. A chill ran down her spine, and suddenly the room felt too warm, too bright, too expectant.

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