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 weight of her childhood bedroom was crushing. Sarah stood in the doorway, hands clasped, surveying the space. Her old posters still adorned the walls, a relic of a younger, more carefree self. Each photograph, each forgotten trinket, reminded her of the distance she'd traveled, and the ground she’d lost.

Her mother knocked lightly, then entered, a hesitant smile on her face. "It's nice to have you home," she said. Sarah forced a smile in response, feeling the tension tighten her shoulders.

"I can help you unpack, if you'd like," her mother offered. The offer was generous, but Sarah felt a prickle of annoyance. She wanted to do this on her own, to reclaim some sense of control. "I’ll manage, thanks," she replied, her voice sharper than intended.

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