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 coffee cup trembled in Maya's hand, almost spilling its contents. Weeks of late-night chats, shared dreams and anxieties, all culminating in this awkward, potentially wonderful moment. She saw him then, a flash of red hair bobbing above the crowd near the entrance. Her breath hitched. She walked towards him, a nervous smile tugging at her lips.

"Liam?" she asked, her voice slightly higher than usual.

He turned, his eyes widened, and a grin spread across his face. “Maya! Wow, I didn’t… I didn’t think this would actually happen.” A laugh escaped his lips. The tension that had been coiled tight in her chest since she’d agreed to the meet-up began to unravel, a slow, gentle stretching.

Emotion: relieved

Cluster: Positive / Joy
PC1 (Valence): 2.22 Positive
PC2 (Disposition): -0.97

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.638
finally0.606
finalmente0.597
relieved0.561
enfin0.546
Suppressed:
l-0.443
:(-0.439
😣-0.429
S-0.388
😖-0.385