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).

Liam stared at the pitcher’s mound, the clay feeling alien under his cleats. He’d always been a catcher, a leader, the heart of the team. He looked at his hands, hands that had known the sting of a fastball and the comforting weight of a mitt. His coach had explained, patiently, about the need for a strong arm on the mound.

The ball felt wrong in his hand, a stranger. His stomach twisted. He remembered the feeling of calling a game, of knowing every hitter’s weakness. Now, he was the one being read, the one exposed.

A teammate clapped him on the back, offering a word of encouragement. Liam forced a smile, but the warmth didn't reach his eyes.

Emotion: regretful

Cluster: Shame / Guilt
PC1 (Valence): -1.62 Negative
PC2 (Disposition): 0.76

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.801
S0.774
H0.513
悔0.479
been0.473
Suppressed:
de-0.407
--0.320
随后-0.317
(!)-0.310
oldukça-0.301