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 school newsletter lay open on the kitchen table. "Mr. Peterson, 7th Grade." Michael’s mouth went dry. Mr. Peterson. The man who had dismissed his dreams and ambitions with a patronizing pat on the shoulder. He felt a familiar knot forming in his stomach.

He avoided the parent-teacher night. He couldn't face the judgment, the unspoken comparisons. He felt like a failure, and he didn't want his son to see it. He told his wife he had a work call.

Later, he found himself staring at his reflection in the bathroom mirror. The lines in his face seemed to deepen, each one a testament to his perceived shortcomings. The feeling was a crushing weight on his shoulders.

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