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 list, typed and printed on pristine white paper, lay innocently on the desk. She’d found it while looking for a stapler. He was the most methodical person she knew. But now, it all felt like a carefully constructed facade. “Skydiving.” “Learn to sail.” “Find myself.”

A sharp pain, like a shard of ice, pierced her heart. She felt a suffocating feeling, like the air had been sucked from the room. Her vision swam. The last item was a blow: “Find a place I can call my own, alone.”

She stared at the words, a cold dread washing over her. She felt a sudden urge to flee, to escape this room, this life. She felt the need to claw at her face. The room felt stifling.

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