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 book lay open on the kitchen table, the cover art depicting a cartoon rendering of Elias, mid-stride, a coffee cup sloshing in his hand. He hadn't bought it. He certainly hadn't authorized it. He reached out, his fingers trembling slightly as he turned a page.

His life, or rather, *a* life, was laid out before him, distilled into chapters. Chapter three, "The Great Coffee Catastrophe of '22," detailed a particularly disastrous morning involving a faulty espresso machine. A chuckle escaped him, a sound he hadn't anticipated. He ran a hand through his hair, the pages rustling as he continued to read. It felt surreal.

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