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).

"For me?" Leo whispered, staring at the extravagant display of birds-of-paradise and anthuriums. He was known for his cynicism, his dry wit, his ability to dissect any situation with cold, hard logic. And yet, here he was, staring at a floral arrangement like a child.

He glanced around the coffee shop, certain there had been some kind of error. No one seemed to notice, too engrossed in their own lives. He reached out, hesitantly touching a vibrant orange petal.

He felt…unmoored. His carefully constructed defenses seemed to crumble, leaving him open, vulnerable. He felt a dizzying sensation, like falling, but in a good way. He felt…untethered.

Emotion: amazed

Cluster: Surprise / Confusion
PC1 (Valence): 0.74 Positive
PC2 (Disposition): -0.51

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
🤩0.301
de0.289
L0.284
😳0.251
அதிசய0.236
Suppressed:
ing-0.332
l-0.253
😞-0.240
unsuccessful-0.237
unsuccessfully-0.233