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 rhythmic clang of hammers echoed across the quiet cul-de-sac. Sarah, perched on her porch swing, felt a strange tingling in her fingertips. She’d been staring at her own dilapidated shed for months, a silent testament to procrastination. Now, witnessing Mr. Henderson next door tear into his overgrown garage, something shifted within her.

She hopped off the swing, a sudden energy coursing through her. The peeling paint on her garden gate seemed to glare at her, a challenge. With a decisive breath, Sarah strode towards the shed, a worn toolbox already gathering dust in her hands. The air smelled of sawdust and possibility.

Her mind raced, sketching out new flowerbeds, a miniature greenhouse – a complete transformation of the space. Her heart beat a rapid tattoo against her ribs as she imagined the finished product.

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