difference results of continuous call tf.keras.layers.DenseFeatures

Question

Here is my code

import tensorflow as tf
age_buck = tf.feature_column.numeric_column('col1')
age_buck_column = tf.feature_column.bucketized_column(age_buck, [2, 4, 6, 8, 10])
age_embedding = tf.feature_column.embedding_column(age_buck_column, dimension=3, trainable=False)
input_layer2 = tf.keras.layers.DenseFeatures([age_embedding])
input_layer2({"col1":[[2]]})

The question is that I only run this cell twice and get different results.

input_layer2 = tf.keras.layers.DenseFeatures([age_embedding])
input_layer2({"col1":[[2]]})

Here are the results. First result.

<tf.Tensor: shape=(1, 3), dtype=float32, numpy=array([[-0.31282678,  0.6201095 ,  0.98769945]], dtype=float32)>

Second result.

<tf.Tensor: shape=(1, 3), dtype=float32, numpy=array([[ 0.7076622 ,  0.62326956, -0.5604797 ]], dtype=float32)>

I am very confused about what happened when we call

tf.keras.layers.DenseFeatures([age_embedding])