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 knelt by the open time capsule, the cold metal reflecting the harsh afternoon sun. The contents were surprisingly banal: a faded photograph, a concert ticket stub, and a collection of loose change. The banality stung. He'd wanted to be remarkable, to leave his mark.

He picked up the photograph. A group of friends, all smiling, all vibrant. He remembered the night, the feeling of belonging. He had ruined that.

The ticket stub was for a band he'd loved, a band heโ€™d never seen live again. The loose change โ€“ meaningless. He closed the lid and buried the capsule again, in the same spot, not wanting anyone else to see the emptiness of his life.

Emotion: self-critical

Cluster: Shame / Guilt
PC1 (Valence): -1.66 Negative
PC2 (Disposition): 1.28

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-critical vector is projected through the unembedding matrix.

Promoted:
L0.748
S0.662
ness0.425
ly0.374
ํƒ“0.351
Suppressed:
la-0.492
soon-0.304
(!)-0.301
secured-0.284
cautiously-0.280