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 attic air tasted of dust and forgotten things. Elias ran a hand through his hair, dislodging a cobweb. He clutched the yellowed paper, his knuckles white. His mother’s handwriting, looping and familiar, stared back at him. *To Whom It May Concern…* His breath hitched. He hadn’t known.

His heart hammered against his ribs. He imagined his mother, young and determined, penning this letter. The revelation felt like a cold splash of water. He remembered their arguments, her disapproval of his career choices. *Maybe I was too judgmental,* he thought, the words echoing in the silence. He folded the letter carefully, then jammed it into his pocket, eager to escape the suffocating space.

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