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).

He leaned against the brick wall, the bass reverberating through his chest. Liam’s eyes were glued to the stage, the guitar riff he’d crafted years ago now a crowd favorite. He had imagined this moment, of course, but it felt different, richer than anything he had conjured.

He reached into his pocket and pulled out a crumpled pack of cigarettes, staring at it for a long moment before putting it back. The energy of the crowd was infectious, a tidal wave of shared joy and appreciation. It was strange. He felt like he was both a part of it, and completely removed from it. He thought about the late nights, the struggle, the dream. He felt a deep, abiding satisfaction, coupled with a strange, bittersweet detachment.

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