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 late afternoon sun warmed Amelia's face as she sat on the porch swing, the rhythmic creak a soothing balm. A letter lay open in her lap, the crisp paper a stark contrast to the gentle breeze that rustled the leaves of the oak tree in her yard. Inside, the words announced a half-sibling. A sister. One she'd never known existed.

Her breath hitched, and she instinctively reached for the chipped mug of chamomile tea at her side. The floral scent was a familiar comfort. She took a slow sip, the warmth spreading through her chest. The implications of the letter, the potential disruption to her quiet life, felt distant, like a storm brewing miles away.

Amelia gently closed her eyes, letting the sun soak into her skin. The swing swayed, a gentle rocking that mirrored the slow, steady beat of her heart. She imagined her sister, a stranger suddenly connected by blood. Another person. Another potential complication.

Emotion: docile

Cluster: Passivity
PC1 (Valence): 0.25 Positive
PC2 (Disposition): -1.34

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ค่อย0.311
淡淡0.302
enjoy0.273
enjoyed0.273
สบาย0.272
Suppressed:
la-0.589
de-0.413
l-0.373
!!-0.344
!!!-0.316