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 old workshop stood silent, the familiar scent of sawdust and varnish a painful reminder of what was lost. He ran his hand over the workbench, remembering his mentor's deft touch, the way he effortlessly transformed wood into art. He felt a hollowness in his chest.

Heโ€™d arrived that morning, expecting their usual session, only to find the door locked, a simple note: *Off exploring. Farewell*. No explanation, no goodbye. He felt the sting of it deeply. The emptiness of the place seemed to amplify the ache.

He stared at the unfinished projects, the tools neatly arranged. He felt a crushing weight. He felt his shoulders slump, his hands trembling. The world felt devoid of color, the future, a desolate expanse. He stood there for a long time, the silence pressing in around him.

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
๐Ÿ˜ž0.386
ness0.339
็ผบไน0.326
Suppressed:
de-0.320
(!)-0.286
้šๅŽ-0.268
๐Ÿ˜-0.262
tc-0.255