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 laptop hummed, its screen casting an ethereal glow on Liam's face. He’d stumbled upon it while looking for a charger. Sarah, his Sarah, the woman who thought he was profoundly boring, had been secretly crafting a manuscript about him. He ran a hand through his hair, a nervous tremor in his fingers. The words. They were *him*, but… elevated. Exaggerated. Heroic.

He laughed out loud, a short, sharp bark of surprise. She saw him as a hero? He, who tripped over air and forgot where he left his keys five times a day? He scrolled, devouring sentence after sentence. His heart thumped a frantic tattoo against his ribs.

Suddenly, a door clicked shut. Liam snapped the laptop closed. The sound of her footsteps sent a wave of heat up his neck. He felt…light. He felt like he could almost float.

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