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 venue was already set up, fairy lights strung across the rafters, tables draped in elegant linen. Olivia's calm façade shattered with a text message: “Karaoke night at Jake’s! BYOB!” Her breath hitched. She'd meticulously booked a string quartet for her sophisticated soirée.

Her carefully crafted seating plan, her perfectly chosen floral arrangements, all felt… wrong. She felt a prickling sensation on her skin, as if a thousand eyes were scrutinizing her. She re-read the message, her knuckles turning white.

She slumped onto a chair, the weight of the planning suddenly crushing her. The crisp white linen seemed to mock her.

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