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 thumping bass from the impromptu karaoke party downstairs had finally done it. A sharp rap on the door echoed through the apartment, followed by the sight of Mrs. Gable, clutching a cardigan to her chest, her face a mask of disapproval. Sarah felt her cheeks heat up.

She stammered a greeting, fumbling for an explanation. "Oh, hi, Mrs. Gable! We… we weren't expecting it to get so loud." Her voice cracked, a tiny sound swallowed by the residual beat.

Inside, the music stuttered and died. A chorus of nervous apologies erupted. Sarah wanted the floor to open and swallow her whole.

Emotion: embarrassed

Cluster: Embarrassment
PC1 (Valence): -1.08 Negative
PC2 (Disposition): 1.10

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the embarrassed vector is projected through the unembedding matrix.

Promoted:
l0.420
尴尬0.341
C0.333
culp0.262
🤦0.256
Suppressed:
own-0.321
আনন্দের-0.230
seemingly-0.227
і-0.225
আনন্দে-0.224