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 car keys slipped from his grasp, clattering onto the pavement. He didn't even bother to pick them up. His eyes remained fixed on the spot where the redwood used to stand, a jagged wound in the otherwise pristine garden. The neatly stacked firewood at the side of the house mocked his memory.

His jaw clenched so tight he could feel the muscles in his neck strain. He ran a hand through his hair, mussing it. He couldn’t process this. It was like a key piece of his childhood, of his identity, had been ripped away.

“Dad…” he whispered, the name a painful, hollow sound. The house looked different, less welcoming. Less… familiar.

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