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).

He slammed his laptop shut, the metallic clang echoing in the otherwise silent library. The library, a sanctuary, now seemed to mock him with its quiet order. His head throbbed. He’d envisioned a future, mapped it out in excruciating detail, all predicated on this scholarship. Now, the map was shredded, a useless tangle of paper. He felt the blood drain from his face.

The other students, heads bowed over their books, seemed miles away, their diligence a sharp contrast to his sudden, paralyzing inertia. He couldn’t bring himself to open his own textbook. The very thought made his stomach clench. He ran a hand through his hair, a nervous gesture he repeated several times.

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