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 aroma of freshly baked bread filled the bakery, but for Olivia, it was a subtle distraction. She leaned against the counter, every bone feeling weighted. The early start had taken its toll, and she felt as if she was underwater.

Her grand-daughter, Chloe, skipped up, holding a crayon drawing aloft. "Grandma, this is Bubbles! He lives in my bubble bath." The drawing depicted a round, jovial figure with a large, smiling face. A flash of recognition sparked in Olivia’s mind.

Bubbles. Her childhood friend from the long summer days. Her gaze softened. A warm, tired feeling settled in her chest. "He seems… cheerful," Olivia said, her voice soft.

Emotion: sleepy

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.86 Negative
PC2 (Disposition): -1.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😴0.318
weary0.310
fatigue0.296
💤0.283
似乎0.280
Suppressed:
B-0.343
C-0.294
because-0.293
భి-0.281
เพราะ-0.277