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 silence in the dimly lit art gallery was suffocating. James, normally captivated by the paintings, couldn't focus on anything but the awkwardness. He'd brought a bottle of wine; the two of them had planned to enjoy an evening of art and conversation. Now it was merely a symbol of how quickly things change.

The other man, Alex, broke the silence first. "So," Alex started, his voice a low rumble, "he told you he was a 'software engineer' too?" The shared lie, the shared deception, hung in the air. James ran a hand through his hair, a nervous gesture he hadn't realized he made. He felt a deep, piercing stab of something akin to shame.

Emotion: sorry

Cluster: Sadness / Despair
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.604
L0.549
😞0.382
😔0.364
ness0.324
Suppressed:
de-0.675
la-0.536
(!)-0.323
!-0.298
l-0.288