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 contents of the safe lay spread across the table: a stack of old currency and a single, tarnished key. Leo felt nothing but a bone-deep exhaustion. The other, better inheritance went to his sister: the family's art collection.

His sister, Elena, was practically skipping with excitement. “Look at this, Leo! A 19th-century gold sovereign! And this key…I bet it unlocks something amazing!” He felt no excitement for her. Just a profound ennui.

He stared at the key, its cold metal reflecting the sterile light of the room. He felt detached, as if watching a movie of someone else's life. He didn’t want the money, the responsibility. He just wanted to disappear.

Emotion: listless

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.03 Negative
PC2 (Disposition): -1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
’0.325
давно0.280
unremarkable0.270
lately0.266
either0.266
Suppressed:
B-0.460
P-0.331
l-0.312
C-0.292
👏-0.273