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 relentless hum of the refrigerator was the soundtrack to Ava's current state. The pressure of the upcoming exams was weighing her down. She entered the dorm, a feeling of deep discouragement settling upon her. She went to her bed, and that’s when she saw it. Her journal was on her roommate's desk, open to a particularly personal entry.

"Seriously, Emily?" Ava asked, her voice trembling. A hollow ache settled in her chest.

Emily averted her gaze, her cheeks flushed. "I… I didn't mean anything by it." Ava felt a profound sense of detachment, as if she were observing herself from a great distance. She just wanted to be left alone.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
😪0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🤟-0.198