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 bus rumbled through the city streets. Sarah stared out the window, the grey buildings blurring into a repetitive pattern. She was lost in thought, her gaze unfocused. The book, *Jane Eyre*, felt heavy in her lap. She’d bought it at the library’s used book sale, hoping for escape.

A thin, brittle note, held together with a faded ribbon, spilled out.

*It doesn’t matter what you do. The end is always the same. So I've stopped trying.* Sarah sighed, a small sound lost in the bus's engine. She tucked the letter back inside the book and rested her head against the window.

Emotion: resigned

Cluster: Passivity
PC1 (Valence): -0.75 Negative
PC2 (Disposition): 0.16

Role in Research

This story is one of 1,000 stories generated for the emotion resigned. 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 resigned stories, after denoising with neutral dialogue baselines, produces the resigned emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the resigned vector is projected through the unembedding matrix.

Promoted:
S0.437
a0.351
que0.323
வதில்லை0.267
sighed0.265
Suppressed:
C-0.375
!-0.316
인해-0.310
Furthermore-0.298
🤩-0.296