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).

Michael slammed the book shut, the sound echoing unnaturally loud in his otherwise quiet apartment. It had landed on his doorstep this morning, a weighty tome chronicling his life. The sheer gall of it, the audacity, left him feeling… off-kilter. He paced, each footfall a heavy thump against the wooden floorboards.

He ran a hand through his hair, tugging at the strands as if to physically pull himself together. The apartment, usually a refuge, now felt like a cage. He couldn’t shake the image of the author, a stranger who now seemingly knew him better than he knew himself. His breathing grew shallow, quick.

He picked up his phone, the familiar weight offering a small measure of comfort. He needed to talk to someone, anyone. The thought of facing the day, of interacting with people who might have read the book, filled him with a potent sense of unease. He felt exposed, stripped bare.

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
😖0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234