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 coffee cup slipped from his grasp, shattering on the tile floor. He stared at the mess, his mind blank. The noise had been going on for hours, a relentless, throbbing pulse.

He began to tremble, his hands shaking so violently he couldn’t pick up the pieces. He ran a hand through his hair, his breath coming in ragged gasps. The anger was there, bubbling just below the surface, but it was overshadowed by something else, a deep, pervasive feeling.

He sank to the floor, curling into a ball. He felt small, insignificant, crushed by the weight of the sound. He closed his eyes, wishing he could just make it all go away.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229