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 awards ceremony. Emily, nervously adjusting her dress, watched as the Best Dessert award was presented. The winner, a celebrated pastry chef, held up a plate of delicate, intricately decorated cupcakes. Emily recognized the base. It was her "Velvet Dreams" recipe, that she gave to her best friend, who was now a food blogger.

Her breath hitched. She felt a sudden, sharp pang in her ribs. She had always been the quiet one, the one who worked in the background. She felt a familiar burn in her eyes. Why did she always let others get ahead?

She excused herself from her table, the music and chatter of the room becoming a blur. The feeling of being completely invisible was crushing.

Emotion: self-critical

Cluster: Shame / Guilt
PC1 (Valence): -1.66 Negative
PC2 (Disposition): 1.28

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.748
S0.662
ness0.425
ly0.374
탓0.351
Suppressed:
la-0.492
soon-0.304
(!)-0.301
secured-0.284
cautiously-0.280