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 sun beat down mercilessly on the practice field, the heat radiating off the artificial turf. The air shimmered, distorting the world. Chloe's vision swam. The coach, Ms. Ramirez, a force of nature in her own right, stood before her, her face unreadable. Chloe could taste the grit in her mouth, the dust that clung to her uniform.

She felt a strange disconnect, as if she were a puppet controlled by invisible strings. The shouts of the other players faded into a distant hum. The coach's eyes, usually so sharp and focused, seemed to pierce right through her. Chloe felt a shiver despite the heat.

Emotion: awestruck

Cluster: Surprise / Confusion
PC1 (Valence): -0.17 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.271
suddenly0.260
stranger0.252
plötzlich0.246
wonder0.242
Suppressed:
la-0.450
싶-0.350
K-0.319
rest-0.248
싶은-0.238