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 phone call had been short, impersonal. "We regret to inform you…" The words echoed in Finn's mind. He gripped the phone tighter, his knuckles white. He stood in the middle of his sparsely furnished apartment, feeling a chill despite the warm afternoon light.

He lowered the phone slowly, his hand trembling. He dropped it onto the table, the sound echoing in the sudden silence. He felt a hollowness, an empty space where ambition and hope had resided.

He went to the window, staring out at the world. The world seemed indifferent, oblivious to his disappointment. He felt a wave of nausea, and he fought the urge to crumble.

Emotion: vulnerable

Cluster: Fear / Anxiety
PC1 (Valence): -2.07 Negative
PC2 (Disposition): -0.69

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.327
ness0.319
😞0.299
😔0.277
😣0.258
Suppressed:
de-0.567
la-0.488
l-0.271
(!)-0.267
(!)-0.257