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 saw's teeth were still fresh, the air thick with the scent of sawdust and broken promises. Amelia stared, hands clenching into fists at her sides. It was just a tree, a sapling really, she’d stuck in the ground when she was seven. Now, a stump. An ugly, raw wound in the perfect green of the park. *Of course*, she thought, the voice inside her a low, relentless drone. *You couldn't even keep a tree alive.*

She remembered the endless watering, the frantic worry during droughts, the childish hope. All for this. She took a step closer, feeling a sharp pang in her chest. Everything she tried, every effort…always a failure.

A squirrel darted across the new space, oblivious. Amelia scoffed, a tight, humorless sound. Even the squirrels were doing better than her, existing without the constant weight of inadequacy.

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
탓0.351
Suppressed:
la-0.492
soon-0.304
(!)-0.301
secured-0.284
cautiously-0.280