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 cold seeped into Sarah’s bones as she stood outside, the wind whipping at her thin coat. She had nothing. Her apartment was a mess, her bank account perpetually empty. Her phone was dead. Now, here. A pawn shop. The building loomed, a concrete testament to her failures.

Inside, the ring was a beacon in the dimness. Grandma Rose’s ring. The tears threatened to spill, but she swallowed them back. Her stomach churned. The pawnbroker said the price, his voice flat. It was a sum she couldn’t even fathom.

She turned and fled, the weight in her chest crushing her. She was a failure, a stain.

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