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 lawyer’s office felt stuffy, the air thick with unspoken truths. David listened, trying to keep his face a mask of composure while the lawyer explained the will and the unexpected inclusion of a half-sister. His grip on the worn leather of the armchair tightened.

His vision swam for a moment, the room tilting precariously. He blinked, forcing himself to focus. He heard the lawyer’s voice, a steady drone, but the words seemed to bounce off a newly erected wall of disbelief.

David excused himself, saying he needed air. Stepping into the street, he found the noise and rush of the city overwhelming. He leaned against a building, the rough brick cool against his skin, trying to catch his breath.

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