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).

Maya sighed, the sound barely audible in the cavernous office. Another rejection. The email sat, unopened, in her inbox. She’d crafted a meticulous cover letter, poured hours into the perfect resume, yet here she was, circling the same dead end. This new information felt like a crack in the dam she'd built around herself, a leak she hadn't anticipated. The DNA results confirming a brother, someone named Daniel, felt like a cruel joke. She needed a new start but couldn't seem to find the means to move forward. She shoved the papers in a drawer, the sharp edges of the folder digging into her palm, a feeling mirroring the way she felt inside.

Emotion: stuck

Cluster: Sadness / Despair
PC1 (Valence): -2.17 Negative
PC2 (Disposition): -0.72

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.487
缺乏0.401
L0.361
每天0.348
stagn0.348
Suppressed:
l-0.472
la-0.346
随后-0.322
undamaged-0.268
C-0.263