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 hammering started before the sun even thought about rising. Amelia pulled the covers over her head, wishing she could disappear completely. Each thud was a fresh indictment, a reminder of her own stalled ambition. She, unlike Mr. Henderson next door, wasn't building anything.

Her breakfast, a bowl of instant oatmeal, sat untouched on the counter. She poked at it with a spoon, the texture of it suddenly repulsive. The renovations next door, this visible manifestation of progress, made her feel small and stagnant. A headache throbbed behind her eyes.

Later, she found herself staring at the blank page of her novel. The cursor blinked, a mocking metronome. She’d been staring at it for hours. She deleted the few clumsy sentences she had written. Then, she opened a browser window and started researching house plants, anything to distract herself from the interior chaos.

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