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 email inbox was empty. Another Tuesday. Today was Daniel’s birthday. It was also the day of Ethan’s camping trip, complete with a bonfire and a band. He'd sent out invitations for a small gathering at his place, but he was getting the feeling he would be on his own.

He ran a hand through his already messy hair, sighing. He reread the rejection email from the job application. He had a degree. He had experience. Yet, here he was, unemployed, unwanted. He felt the familiar weight settle in his chest.

He stared at his reflection, a stranger staring back. He was a nonentity. Why would anyone want to celebrate with him, anyway? He should probably just turn off his phone and hide.

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