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 shelves of the library loomed over her, the books a silent rebuke. She had spent years immersed in research, guided by her mentor, Dr. Albright. Now, his absence was a gaping hole in her life. The silence in the library felt oppressive.

She picked up a worn volume, running her fingers along the spine. She felt a tremor run through her body. His last message was a simple, business-like email. Nothing personal. No acknowledgment of their years of collaboration. The emptiness felt complete.

She sat at a table, unable to concentrate. The words blurred before her eyes, the sentences failing to register. She felt a profound sense of isolation, a feeling that no one else understood the magnitude of the loss. Her vision blurred, and she felt tears welling.

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