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 spare room was thick with the scent of lavender and old paper. Emily felt a familiar constriction in her chest. She was supposed to be sorting through her mother's belongings. She felt the heavy weight of it all pressing down on her.

She found a brightly decorated box labeled "Emily’s Early Adventures." Inside, a plethora of schoolwork. A meticulously crafted diorama of a historical battle. A detailed essay on the Civil War. A series of perfectly executed penmanship drills.

She remembered the joy she had taken in these tasks. The validation she’d felt. Now, she felt nothing but an overwhelming sense of inadequacy. A cold wash of indifference ran through her.

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
😞0.386
ness0.339
缺乏0.326
Suppressed:
de-0.320
(!)-0.286
随后-0.268
😍-0.262
tc-0.255