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).

He felt the sudden coldness in his palms. David clenched them into fists, knuckles white, forcing himself not to bolt. The low hum of the air conditioning, usually a comfort, now grated on his nerves. He'd recognized the intricate filigree immediately.

“How much?” His voice sounded thick, foreign. He hated the way it trembled. He ran a hand through his hair, dislodging strands he didn't even realize he was touching.

The pawn broker, a burly man with a gold chain glinting in the dim light, named a price. It was far less than the ring's worth, a further insult. David's vision blurred, and the images of his grandmother laughing with his grandfather at the dinner table flashed before his eyes. He had to breathe.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290