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 artist, Sarah, found herself unable to avert her eyes. Her nephew, Ethan, had drawn a playful figure with flowing hair, just like the one she had. It stirred a dormant part of her, a place she hadn't visited in ages. She blinked away the sudden moisture in her eyes.

She gathered her paints, the familiar scents of linseed oil and turpentine invigorating her senses. A canvas, previously ignored, was now calling to her. Her hands felt eager, almost impatient.

She began to paint, the colors merging into a symphony of light and shadow, emotion and memory. She worked for hours, until the room was thick with the scent of paint, a warmth blooming in her chest.

Emotion: inspired

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.04

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.563
invigor0.465
newfound0.446
هذ0.414
используя0.406
Suppressed:
😞-0.481
不-0.431
worse-0.428
😣-0.400
fact-0.389