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).

Liam was practicing his speech in front of the mirror, adjusting his tie. He’d envisioned a refined dinner party, a sophisticated evening with his closest friends. Then he got the text: “Party at Chloe’s! Karaoke, glow sticks, the works!” He sighed, the image of his meticulously curated playlist disintegrating in his mind.

He knew Chloe's parties. They were a whirlwind of noise and frenetic energy. He imagined himself, awkwardly standing in a corner, clutching a glass of something expensive, utterly out of his depth. A bead of sweat trickled down his temple.

He decided to call Chloe, but his finger hovered over the dial button. What could he even say? He let out a long breath and slowly walked over to his piano. It was the only thing that could calm him down.

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