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 pawn shop’s stale air was familiar to Noah. He sought refuge here from the world outside, a world that seemed to move at a pace he couldn't grasp. The days blurred together, an endless cycle of routine. He felt like he was trapped, caught in a swirling vortex. He found himself drawn to a case, filled with trinkets and forgotten treasures. And there it was. His grandmother’s ring, the intricate Celtic design, the emerald sparkling faintly.

A rush of memories flooded back, fleeting and then gone. He’d barely known his grandmother. He paid for it, and the transaction was like everything else: empty. He walked out of the shop, the sun a blazing orb in the sky. He had to go somewhere, anywhere.

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