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 rang, shattering the fragile peace of the afternoon. Liam ignored it, the incessant hammering outside already fraying his nerves. He hated it when people attempted to contact him when he was preoccupied, even when the source of his preoccupation was only a small thing.

He retreated into the back room, pulling the curtains. The sun, once a comforting presence, now seemed to mock him. The noise intensified, each blow of the hammer sending a jolt of anxiety through him.

He slammed his fist on the table, a sudden, explosive release of tension. He wanted it to stop. He wanted them to leave him alone. He felt a deep, profound sense of helplessness.

Emotion: disturbed

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.318
ness0.309
无法0.300
😞0.297
worse0.284
Suppressed:
de-0.829
la-0.666
a-0.392
B-0.301
"-0.290