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 keys clattered against the tiled floor as he dropped them, the sound amplified in the sudden silence of the empty driveway. A leaden sensation spread through his limbs. The world seemed to dim slightly. He crouched, retrieving the keys, his movements sluggish and deliberate.

He had promised Maya a ride to the movies. Now, he would have to call and cancel. He hated letting her down. The feeling of utter disappointment in himself was a heavy shroud, making the world feel grey.

He walked back inside, the empty space where his pickup truck had been a constant, mocking reminder. He knew that the only way to fix it was to go and retrieve his car. But first, he needed a moment, alone.

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