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).

He had always hated her family's Sunday dinners. The loud, boisterous conversations in Ukrainian, the unfamiliar foods. Now, she was at the table, her aunt serving her a plate of varenyky. He was there too, sitting beside her, listening attentively. Then, with a hesitant smile, he began speaking. "Dobryj den'."

A strange lightness filled her chest. She had pleaded and begged him to learn, but it had always been a lost cause. He never even tried. Now, he was actually trying. She felt a lump form in her throat, a physical manifestation of the emotion she couldn't name.

She reached for his hand under the table, squeezing it tightly.

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