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).

She sat at the kitchen table, staring at the empty space where the "For Sale" sign would soon be. The landlord’s words, "investment," "opportunity," and "market value" echoed in her head. They were empty words, devoid of feeling.

She picked at a loose thread on her sweater, her fingers trembling. The apartment, with its quirky layout and the faded paint, was a reflection of her. Now, that reflection was being distorted, commodified.

She rose from the table, her legs unsteady. She needed to escape. She headed for the back door. As she did, she almost walked into the wall. She had to take a few steps back to continue.

Emotion: trapped

Cluster: Sadness / Despair
PC1 (Valence): -3.02 Negative
PC2 (Disposition): -0.80

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.573
ness0.401
无法0.366
hopeless0.360
😞0.353
Suppressed:
la-0.740
de-0.376
l-0.339
several-0.323
excitedly-0.322