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 antique clock on the mantelpiece ticked loudly, each second a hammer blow against Eleanor’s skull. The house, usually a sanctuary, felt oppressive, the shadows in the corners deepening as the day drew to a close. She sat by the window, the worn armchair doing little to soothe her.

Her niece’s drawings arrived in a hastily scribbled note from her sister. A drawing of a towering, thin figure. It was the same one Eleanor used to whisper secrets to, as a child, the one she’d all but forgotten.

The weight of the past pressed on her, a physical sensation she couldn’t shake. The memories, once faint whispers, now clamored for attention. Eleanor felt a powerful longing for something she couldn't name, a past she could never truly reclaim.

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