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 headline screamed at him from his phone screen. "Student's Essay a Shining Example!" He felt a knot in his throat. He’d submitted that essay hoping for a scholarship, but now it felt like a betrayal. His privacy, once a safe harbor, was breached.

He retreated to his room, pulling the blinds shut. The sudden darkness was a relief. He lay on his bed, staring at the ceiling, feeling profoundly unsettled. He turned on some ambient music, trying to create a space that would contain his feelings.

He eventually fell into a fitful sleep, tossing and turning, the words from his essay echoing in his dreams.

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
πŸ˜”0.364
ness0.324
Suppressed:
de-0.675
la-0.536
(!)-0.323
!-0.298
l-0.288