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).

He stared at the television screen, the image of his childhood friend, now a celebrity chef, beaming as he demonstrated his “Grandma’s Special Dumplings.” The recipe was a family heirloom, carefully passed down through generations. He hadn't known his friend would use the recipe.

He felt a knot of anger and... something else, a deep, sinking sadness. The room felt suddenly too small, too close. He wanted to shout, but the words caught in his throat. He ran a hand through his hair, the gesture a nervous tic.

He picked up the remote, clicked the power button, and the screen went black, the silence almost deafening. He wanted to forget the entire encounter.

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