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 elevator ride felt interminable. He squeezed his eyes shut as the numbers slowly climbed. He felt like a coiled spring, ready to snap. The lobby itself was a labyrinth of hushed tones and subdued lighting, each element seeming designed to heighten his disquiet.

The therapist's door opened, and a woman with a deceptively sweet smile emerged. It was Rebecca, the girl who had turned his life into a series of public humiliations. She extended a hand, her voice a calm whisper.

β€œCome in, Thomas,” she said, her gaze unwavering. He slowly began to walk towards her. Each step was a battle.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
πŸ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198