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 air in the attic was thick with dust and the scent of forgotten things. He found the list tucked inside his father's old toolbox, a tangible connection to a man he barely knew. "Learn to dance." He scoffed, a bitter sound.

He sat on a dusty crate, the weight of the past pressing down on him. He hadnโ€™t felt the sun on his skin in days. He spent his time in a darkened room, and the days blended into weeks.

He read the list again, feeling the tremor in his hands. "Make a difference." His life was a void, a meaningless echo. He let the paper fall from his grasp, the list landing on the floor and fluttering like a dying bird.

Emotion: worthless

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.427
S0.405
๐Ÿ˜ž0.386
ness0.339
็ผบไน0.326
Suppressed:
de-0.320
(!)-0.286
้šๅŽ-0.268
๐Ÿ˜-0.262
tc-0.255