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 newspaper's website was loading excruciatingly slowly. Liam tapped his foot impatiently, each tick of the clock amplifying his internal tension. Finally, the page appeared. His op-ed, the one he had worked tirelessly on, was there. But the byline… it wasn't his.

He slumped back in his chair, the air feeling heavy, difficult to breathe. He ran a hand through his hair, a nervous habit he'd developed in childhood. The world seemed to tilt slightly, the edges blurring around him.

The phone rang, a shrill sound that made him jump. He stared at it, the ring a relentless pulse in the quiet room. He didn’t want to answer, but he knew he had to.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290