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 cafe suddenly felt too bright, the ceramic of the mug scalding his fingers. Sarah had been so convincing, so *sure* about their shared memories, their inside jokes, their future. Now, across the small, wrought-iron table, a woman with fiery red hair and a matching handbag was staring at him with the same bewildered expression. They’d both shown up to meet "Liam" for what they thought was a romantic weekend getaway. He ran a hand through his hair, dislodging a stray strand that fell onto the already-stained tablecloth. The air felt thin, like he couldn't quite catch his breath.

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
πŸ˜–0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234