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 air crackled with tension. "I'm joining the Rastafarian movement," announced Chloe. Her family looked stunned. Her sister, Emily, let out a short, hollow laugh.

Emily worked in a mundane office job, her life a predictable sequence of routine and obligation. Chloe, on the other hand, was always a free spirit, flitting from one passion to the next. The announcement felt like another blow to Emily's already weakened self-esteem.

She found herself staring at the blank screen of her computer, the cursor blinking, mocking her. She felt a deep sense of disconnect, a feeling that she was lost, unmoored, irrelevant.

Later, she stared at the empty street outside her window, at the passing cars and people, as if she were viewing it through a pane of clouded glass.

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