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).

He walked aimlessly, the wind whipping at his face. The rejection letter burned in his pocket. The city, usually a vibrant tapestry of life, now seemed bleak and desolate. He felt isolated, an outcast. His heart ached, a raw, insistent throb.

He sat on a cold, concrete bench, watching the passing crowds. He felt their collective indifference. Each smiling face was a reminder of his own perceived failings. He felt a sense of inadequacy, a deep-seated belief that he wasn't enough.

He closed his eyes, the image of his shattered dreams a constant presence. The weight of his disappointment was a heavy cloak, binding him to the spot.

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