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 attic air, thick with dust motes dancing in the lone sunbeam, felt… different. Amelia swung the heavy door open, a lightness in her chest she hadn't known in years. Gone was the familiar ache of routine, replaced by a fizzing excitement. She inhaled deeply, the musty scent strangely invigorating.

She poked through the boxes. A chipped porcelain doll, eyes staring blankly at the rafters. A stack of yellowed letters tied with a faded ribbon. Picking up the letters, Amelia felt a smile creep across her face; she’d start reading them later. She could hear her own pulse thrumming in her ears.

A small wooden chest sat tucked away in a corner. Amelia’s fingers, newly agile, fumbled with the clasp. Inside, nestled amongst velvet lining, lay a collection of colorful paintbrushes and a half-used tube of crimson. She imagined herself with a canvas, creating something.

Emotion: rejuvenated

Cluster: Positive / Joy
PC1 (Valence): 3.32 Positive
PC2 (Disposition): -0.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.547
de0.526
newfound0.523
invigor0.495
rejuvenated0.495
Suppressed:
😞-0.485
😣-0.451
不-0.434
worse-0.419
😥-0.385