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).

Rain lashed against the windows of Maya's cramped apartment, mirroring the mood that had settled over her. She stared at the overflowing recycling bin, the image of it a constant, unwelcome companion. The air hung thick with the scent of stale coffee and unfulfilled ambitions.

Across the hall, Mrs. Gable was known to her as a kind, elderly woman who always offered freshly baked cookies. Mrs. Gable's small house appeared perfectly ordinary.

One afternoon, Maya accidentally saw a delivery man struggling to maneuver a grand piano through Mrs. Gable's front door. The sight, the incongruity, caused a knot to tighten in Maya's gut. The piano was not small.

The next day, she saw a sleek, expensive car parked in Mrs. Gable's previously empty garage. The discovery filled her with a strange, heavy weight.

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