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 sterile white of the hospital room seemed to amplify the bleakness within. He stared at the ceiling, the fluorescent lights a relentless assault. His hands, usually steady, were now twitching uncontrollably, a betrayal of his body. He felt a constant, low-grade thrum of anxiety, a buzzing beneath his skin. He hadn't slept properly in days.

The doctor, a young woman with kind eyes, entered the room, holding a file. She looked at him with a gentle concern. "I have some new test results," she began softly. "They're... unusual. But I think I’ve found someone else."

Her words sparked a flicker of something in his chest, a flicker of something he had forgotten existed.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240