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 ceramic mug warmed Sarah’s hands, but the heat didn’t extend to her core. It was icy. Her sister, Emily, had just declared her intention to become a Buddhist. Sarah stared at the swirling tea leaves, trying to decipher a future they suddenly didn't share.

A tremor started in her jaw. She hadn't expected this. Emily, the pragmatist, the one who always scoffed at anything remotely "woo-woo." Now this.

“So, you’re just…changing everything?” The question sounded small, even to her own ears. Emily smiled, a placid, unsettling smile. The air in the kitchen felt thin, like the oxygen had been sucked out.

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