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).

"So, ready to move on, eh?" Gary, her former boss, clapped her on the back. Sarah winced slightly, the gesture feeling somehow intrusive. She nodded, forcing a smile.

She stood in the doorway of the office she had occupied for the past ten years, a small, corner space in the legal department. The familiar clutter of law books, the framed diplomas, the worn leather of her chair—all now seemed to hold a special significance.

She took one last, lingering look at the space, the memories of late nights, stressful meetings, and hard-fought victories flooding her mind. She closed her eyes for a moment, letting the feelings wash over her before forcing herself to turn away.

Emotion: sentimental

Cluster: Nostalgia / Reflection
PC1 (Valence): 0.89 Positive
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.677
fondly0.567
memories0.503
曾0.488
reminis0.466
Suppressed:
either-0.515
or-0.488
[]-0.473
--0.408
не-0.396