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).

Her hands were clammy, despite the air conditioning blasting in her apartment. The text message had hit her like a physical blow: "Hey, are you free for a coffee? I'm, uh, right around the corner." Her heart hammered against her ribs, a frantic drumbeat against the silence. It was all a blur.

She replayed their last conversation in her head, searching for clues, for anything she might have missed, anything that might explain why he was *here*, in her city. Every seemingly innocent question, every off-hand remark suddenly felt loaded with subtext. She felt herself start to hyperventilate.

She paced. Should she answer? Should she ignore it? The phone felt heavy in her hand, a weighty burden of digital connection and sudden, terrifying proximity. The world narrowed to the confines of her small apartment, a cage of anxiety and anticipation.

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